[
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b1da82a91856d8d",
    "variant": "GPT-6 Astra (max)",
    "score": 52.6737,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7070b585da6e3a29",
    "variant": "GPT-6 Astra (xhigh)",
    "score": 52.3863,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7c09034755a992fc",
    "variant": "GPT-6 Astra (high)",
    "score": 50.9191,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3cf95b4f1be42e0f",
    "variant": "GPT-6 Astra (medium)",
    "score": 49.5704,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6858c62f40a2b8a3",
    "variant": "GPT-6 Astra (low)",
    "score": 45.7819,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:e5bdec03718dfb8f",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 58.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 55.39,
    "score_high": 60.97,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:d1970c4faffe81bc",
    "variant": "Codex - GPT-6 Astra (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 55.160000000000004,
    "score_high": 60.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:425d97cf71b364f9",
    "variant": "Codex - GPT-6 Astra (high)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 54.910000000000004,
    "score_high": 60.85,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1ebcc077b6f11845",
    "variant": "Codex - GPT-6 Astra (medium)",
    "score": 54.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.58,
    "score_high": 56.900000000000006,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:6c09cda642c293be",
    "variant": "Codex - GPT-6 Astra (low)",
    "score": 50.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 47.86,
    "score_high": 53.36,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:700453154be041cb",
    "variant": "Artificial Analysis - GPT-6 Astra (xhigh)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e44812025afd889c",
    "variant": "Artificial Analysis - GPT-6 Astra (max)",
    "score": 59.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:12ee7971061ca0e0",
    "variant": "Artificial Analysis - GPT-6 Astra (high)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0634c4abcbad70cc",
    "variant": "Artificial Analysis - GPT-6 Astra (medium)",
    "score": 49.4949,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4785a3610e775817",
    "variant": "Artificial Analysis - GPT-6 Astra (low)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "arena_code",
    "configuration_id": "arena_code:2fa5b191581aaf87",
    "variant": "gpt-6-astra-max",
    "score": 1789,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1778.6,
    "score_high": 1799.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:704fea58650c673b",
    "variant": "GPT 6 Astra (Max)",
    "score": 12.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.9,
    "score_high": 14.459999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6ee94ff7d755eeee",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 61.645,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.4671,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:c64a6ebb32778718",
    "variant": "Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium",
    "score": 58.8884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.5365,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:eab6a68a5b32527b",
    "variant": "GPT-6 Astra",
    "score": 82.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.612939,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aa4ad931eff45be4",
    "variant": "mini-swe-agent - gpt-6-astra (xhigh)",
    "score": 74.11504424778761,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 71.24964807371246,
    "score_high": 76.98044042186275,
    "mean_cost_usd_per_task": 6.52377356460177,
    "median_cost_usd_per_task": 5.6717151,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e8101649c60ecba8",
    "variant": "mini-swe-agent - gpt-6-astra (high)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 69.80659243770221,
    "score_high": 76.65358455344823,
    "mean_cost_usd_per_task": 5.723721956194691,
    "median_cost_usd_per_task": 4.9622669,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b30a594ec5f66ce7",
    "variant": "mini-swe-agent - gpt-6-astra (max)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 72.39976873936956,
    "score_high": 74.06040825178087,
    "mean_cost_usd_per_task": 12.369032401327434,
    "median_cost_usd_per_task": 11.036936,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a5c5cd4b12673627",
    "variant": "mini-swe-agent - gpt-6-astra (medium)",
    "score": 72.78761061946902,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 70.19796153763716,
    "score_high": 75.37725970130089,
    "mean_cost_usd_per_task": 4.379527705752213,
    "median_cost_usd_per_task": 3.7133415999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2d2b1fb9f6df06a3",
    "variant": "mini-swe-agent - gpt-6-astra (low)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 65.73453717840262,
    "score_high": 68.33625928177437,
    "mean_cost_usd_per_task": 2.188762706637168,
    "median_cost_usd_per_task": 1.7209886,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ca545106241767d7",
    "variant": "GPT-6 Sol (max)",
    "score": 47.5276,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ec3291a5ccf1d360",
    "variant": "GPT-6 Sol (xhigh)",
    "score": 44.101,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b88d90b9ef2bcc13",
    "variant": "GPT-6 Sol (high)",
    "score": 42.8216,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5dea08c56cadf0a5",
    "variant": "GPT-6 Sol (medium)",
    "score": 39.7821,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db3deb60f0a6f0ac",
    "variant": "GPT-6 Sol (low)",
    "score": 33.9009,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:49ed8f07e3584753",
    "variant": "GPT-6 Sol (non-reasoning)",
    "score": 28.0922,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c54c846fa56e7fb9",
    "variant": "Artificial Analysis - GPT-6 Sol (max)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ba48609dee4ff716",
    "variant": "Artificial Analysis - GPT-6 Sol (xhigh)",
    "score": 30.303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2ac75acfdd5556ef",
    "variant": "Artificial Analysis - GPT-6 Sol (high)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b54a5c8b54994f4",
    "variant": "Artificial Analysis - GPT-6 Sol (medium)",
    "score": 18.6869,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ba96dfd07fb6e2bc",
    "variant": "Artificial Analysis - GPT-6 Sol (non-reasoning)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:af9e50a31779df75",
    "variant": "Artificial Analysis - GPT-6 Sol (low)",
    "score": 9.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:99658ae7db6b17a4",
    "variant": "gpt-6-sol-max",
    "score": 1689,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1677.2,
    "score_high": 1700.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c3f5ba38fbb30407",
    "variant": "GPT 6 Sol (Max)",
    "score": 10.65,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 8.08,
    "score_high": 13.22,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.91,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:a5a1b714fe3ad343",
    "variant": "Codex - GPT-6 Sol (max)",
    "score": 56.6626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.9897,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:63b060c2709bd850",
    "variant": "GPT-6 Sol",
    "score": 89.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.296641,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e41e4b6709da24d4",
    "variant": "GPT-6 Luna (max)",
    "score": 37.256,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:711bafc42ade2516",
    "variant": "GPT-6 Luna (xhigh)",
    "score": 33.8846,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:927f29d66e09bcc0",
    "variant": "GPT-6 Luna (high)",
    "score": 32.1482,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:51051c5b6fc81a75",
    "variant": "GPT-6 Luna (medium)",
    "score": 29.462,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9e4a1080bc5cdeda",
    "variant": "GPT-6 Luna (low)",
    "score": 20.9225,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be701ec71aacde7a",
    "variant": "GPT-6 Luna (non-reasoning)",
    "score": 18.2617,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4d4153eb38f2e84f",
    "variant": "Artificial Analysis - GPT-6 Luna (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3956f4765e345bfa",
    "variant": "Artificial Analysis - GPT-6 Luna (xhigh)",
    "score": 8.0808,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:964384bb8d3b9a13",
    "variant": "Artificial Analysis - GPT-6 Luna (high)",
    "score": 4.5455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:62b32b0accfdc3e1",
    "variant": "Artificial Analysis - GPT-6 Luna (medium)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c911fafd76fe1373",
    "variant": "Artificial Analysis - GPT-6 Luna (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1f723b35d187e5ec",
    "variant": "Artificial Analysis - GPT-6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:27376aa104f48f0e",
    "variant": "gpt-6-luna-max",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1573.0,
    "score_high": 1591.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:04bd9ba65c143398",
    "variant": "GPT 6 Luna (Max)",
    "score": 1.68,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 0.27,
    "score_high": 3.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.06,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:01e2ffcaa1665576",
    "variant": "Codex - GPT-6 Luna (max)",
    "score": 41.0744,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.1759,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6-luna",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:df380d7af56a8dd0",
    "variant": "GPT-6 Luna",
    "score": 83.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.015871,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6ad871a45a4a5df",
    "variant": "GPT-6.1 Sol (max)",
    "score": 51.8333,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4a8f2c60cc909b11",
    "variant": "GPT-6.1 Sol (xhigh)",
    "score": 51.0378,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:aea0241d837a4380",
    "variant": "GPT-6.1 Sol (high)",
    "score": 50.2378,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e4a9f446e946fc59",
    "variant": "GPT-6.1 Sol (medium)",
    "score": 47.7833,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f49734a44b6bfe83",
    "variant": "GPT-6.1 Sol (low)",
    "score": 42.0836,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f935d95ba064b29b",
    "variant": "Artificial Analysis - GPT-6.1 Sol (max)",
    "score": 56.0606,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:94af356c207fc48e",
    "variant": "Artificial Analysis - GPT-6.1 Sol (xhigh)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c77efb6f723a47b3",
    "variant": "Artificial Analysis - GPT-6.1 Sol (high)",
    "score": 51.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8f793b0822f5faf4",
    "variant": "Artificial Analysis - GPT-6.1 Sol (medium)",
    "score": 47.9798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:11dc57e4e600b27d",
    "variant": "Artificial Analysis - GPT-6.1 Sol (low)",
    "score": 30.8081,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:8cc100910da385f3",
    "variant": "gpt-6.1-sol-max",
    "score": 1759,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1739.9,
    "score_high": 1778.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f60c3eaad821549",
    "variant": "Codex - GPT-6.1 Sol (xhigh)",
    "score": 62.9078,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.0397,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:0e50f95e98c947c2",
    "variant": "Codex - GPT-6.1 Sol (medium)",
    "score": 61.4147,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.7047,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6adf1a461abaf0f2",
    "variant": "Codex - GPT-6.1 Sol (high)",
    "score": 60.1492,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.8892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:718b49f369ed6f33",
    "variant": "Codex - GPT-6.1 Sol (max)",
    "score": 60.1475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.5541,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:79db3062d86f1bbd",
    "variant": "Codex - GPT-6.1 Sol (low)",
    "score": 57.2163,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4988,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-6.1-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:1f49b4d125f7e8d5",
    "variant": "GPT-6.1 Sol",
    "score": 90.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.38203,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b1da82a91856d8d",
    "variant": "GPT-6 Astra (max)",
    "score": 52.6737,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7070b585da6e3a29",
    "variant": "GPT-6 Astra (xhigh)",
    "score": 52.3863,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7c09034755a992fc",
    "variant": "GPT-6 Astra (high)",
    "score": 50.9191,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3cf95b4f1be42e0f",
    "variant": "GPT-6 Astra (medium)",
    "score": 49.5704,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6858c62f40a2b8a3",
    "variant": "GPT-6 Astra (low)",
    "score": 45.7819,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:e5bdec03718dfb8f",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 58.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 55.39,
    "score_high": 60.97,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:d1970c4faffe81bc",
    "variant": "Codex - GPT-6 Astra (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 55.160000000000004,
    "score_high": 60.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:425d97cf71b364f9",
    "variant": "Codex - GPT-6 Astra (high)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 54.910000000000004,
    "score_high": 60.85,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1ebcc077b6f11845",
    "variant": "Codex - GPT-6 Astra (medium)",
    "score": 54.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.58,
    "score_high": 56.900000000000006,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:6c09cda642c293be",
    "variant": "Codex - GPT-6 Astra (low)",
    "score": 50.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 47.86,
    "score_high": 53.36,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:700453154be041cb",
    "variant": "Artificial Analysis - GPT-6 Astra (xhigh)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e44812025afd889c",
    "variant": "Artificial Analysis - GPT-6 Astra (max)",
    "score": 59.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:12ee7971061ca0e0",
    "variant": "Artificial Analysis - GPT-6 Astra (high)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0634c4abcbad70cc",
    "variant": "Artificial Analysis - GPT-6 Astra (medium)",
    "score": 49.4949,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4785a3610e775817",
    "variant": "Artificial Analysis - GPT-6 Astra (low)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "arena_code",
    "configuration_id": "arena_code:2fa5b191581aaf87",
    "variant": "gpt-6-astra-max",
    "score": 1789,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1778.6,
    "score_high": 1799.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:704fea58650c673b",
    "variant": "GPT 6 Astra (Max)",
    "score": 12.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.9,
    "score_high": 14.459999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6ee94ff7d755eeee",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 61.645,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.4671,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:c64a6ebb32778718",
    "variant": "Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium",
    "score": 58.8884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.5365,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:eab6a68a5b32527b",
    "variant": "GPT-6 Astra",
    "score": 82.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.612939,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aa4ad931eff45be4",
    "variant": "mini-swe-agent - gpt-6-astra (xhigh)",
    "score": 74.11504424778761,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 71.24964807371246,
    "score_high": 76.98044042186275,
    "mean_cost_usd_per_task": 6.52377356460177,
    "median_cost_usd_per_task": 5.6717151,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e8101649c60ecba8",
    "variant": "mini-swe-agent - gpt-6-astra (high)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 69.80659243770221,
    "score_high": 76.65358455344823,
    "mean_cost_usd_per_task": 5.723721956194691,
    "median_cost_usd_per_task": 4.9622669,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b30a594ec5f66ce7",
    "variant": "mini-swe-agent - gpt-6-astra (max)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 72.39976873936956,
    "score_high": 74.06040825178087,
    "mean_cost_usd_per_task": 12.369032401327434,
    "median_cost_usd_per_task": 11.036936,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a5c5cd4b12673627",
    "variant": "mini-swe-agent - gpt-6-astra (medium)",
    "score": 72.78761061946902,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 70.19796153763716,
    "score_high": 75.37725970130089,
    "mean_cost_usd_per_task": 4.379527705752213,
    "median_cost_usd_per_task": 3.7133415999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2d2b1fb9f6df06a3",
    "variant": "mini-swe-agent - gpt-6-astra (low)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 65.73453717840262,
    "score_high": 68.33625928177437,
    "mean_cost_usd_per_task": 2.188762706637168,
    "median_cost_usd_per_task": 1.7209886,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b1da82a91856d8d",
    "variant": "GPT-6 Astra (max)",
    "score": 52.6737,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7070b585da6e3a29",
    "variant": "GPT-6 Astra (xhigh)",
    "score": 52.3863,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7c09034755a992fc",
    "variant": "GPT-6 Astra (high)",
    "score": 50.9191,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3cf95b4f1be42e0f",
    "variant": "GPT-6 Astra (medium)",
    "score": 49.5704,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6858c62f40a2b8a3",
    "variant": "GPT-6 Astra (low)",
    "score": 45.7819,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:e5bdec03718dfb8f",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 58.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 55.39,
    "score_high": 60.97,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:d1970c4faffe81bc",
    "variant": "Codex - GPT-6 Astra (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 55.160000000000004,
    "score_high": 60.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:425d97cf71b364f9",
    "variant": "Codex - GPT-6 Astra (high)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 54.910000000000004,
    "score_high": 60.85,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1ebcc077b6f11845",
    "variant": "Codex - GPT-6 Astra (medium)",
    "score": 54.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.58,
    "score_high": 56.900000000000006,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:6c09cda642c293be",
    "variant": "Codex - GPT-6 Astra (low)",
    "score": 50.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 47.86,
    "score_high": 53.36,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:700453154be041cb",
    "variant": "Artificial Analysis - GPT-6 Astra (xhigh)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e44812025afd889c",
    "variant": "Artificial Analysis - GPT-6 Astra (max)",
    "score": 59.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:12ee7971061ca0e0",
    "variant": "Artificial Analysis - GPT-6 Astra (high)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0634c4abcbad70cc",
    "variant": "Artificial Analysis - GPT-6 Astra (medium)",
    "score": 49.4949,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4785a3610e775817",
    "variant": "Artificial Analysis - GPT-6 Astra (low)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "arena_code",
    "configuration_id": "arena_code:2fa5b191581aaf87",
    "variant": "gpt-6-astra-max",
    "score": 1789,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1778.6,
    "score_high": 1799.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:704fea58650c673b",
    "variant": "GPT 6 Astra (Max)",
    "score": 12.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.9,
    "score_high": 14.459999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6ee94ff7d755eeee",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 61.645,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.4671,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:c64a6ebb32778718",
    "variant": "Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium",
    "score": 58.8884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.5365,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:eab6a68a5b32527b",
    "variant": "GPT-6 Astra",
    "score": 82.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.612939,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aa4ad931eff45be4",
    "variant": "mini-swe-agent - gpt-6-astra (xhigh)",
    "score": 74.11504424778761,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 71.24964807371246,
    "score_high": 76.98044042186275,
    "mean_cost_usd_per_task": 6.52377356460177,
    "median_cost_usd_per_task": 5.6717151,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e8101649c60ecba8",
    "variant": "mini-swe-agent - gpt-6-astra (high)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 69.80659243770221,
    "score_high": 76.65358455344823,
    "mean_cost_usd_per_task": 5.723721956194691,
    "median_cost_usd_per_task": 4.9622669,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b30a594ec5f66ce7",
    "variant": "mini-swe-agent - gpt-6-astra (max)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 72.39976873936956,
    "score_high": 74.06040825178087,
    "mean_cost_usd_per_task": 12.369032401327434,
    "median_cost_usd_per_task": 11.036936,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a5c5cd4b12673627",
    "variant": "mini-swe-agent - gpt-6-astra (medium)",
    "score": 72.78761061946902,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 70.19796153763716,
    "score_high": 75.37725970130089,
    "mean_cost_usd_per_task": 4.379527705752213,
    "median_cost_usd_per_task": 3.7133415999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2d2b1fb9f6df06a3",
    "variant": "mini-swe-agent - gpt-6-astra (low)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 65.73453717840262,
    "score_high": 68.33625928177437,
    "mean_cost_usd_per_task": 2.188762706637168,
    "median_cost_usd_per_task": 1.7209886,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_max::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_pro::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a795ed51d673418d",
    "variant": "Gemini 3.8 Flash (high)",
    "score": 40.9262,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8f226080bd0bde9a",
    "variant": "Gemini 3.8 Flash (medium)",
    "score": 39.774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e0b41460917d3eff",
    "variant": "Gemini 3.8 Flash (low)",
    "score": 33.4548,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:206ddf92cd474c5f",
    "variant": "mini-SWE-agent - Gemini 3.8 Flash (high)",
    "score": 19.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 15.73,
    "score_high": 22.45,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a1eae5d167a32a34",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (medium)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a0853cb96c8ece1",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (high)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:76b42aa2f87efd5c",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (low)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:cee78179b654f666",
    "variant": "gemini-3.8-flash-high",
    "score": 1583,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1575.1,
    "score_high": 1590.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:60a00778bc1492a5",
    "variant": "Gemini 3.8 Flash (High)",
    "score": 2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 2.14,
    "score_high": 3.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.58,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:68de21286728c605",
    "variant": "Antigravity SDK - Gemini 3.8 Flash (high)",
    "score": 41.8632,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Antigravity SDK v0.1.12",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.4674,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e5b1ca76e59dabd0",
    "variant": "Gemini 3.8 Flash",
    "score": 68.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.210201,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a4e0e06e8292b616",
    "variant": "mini-swe-agent - gemini-3-8-flash (high)",
    "score": 73.8255033557047,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 72.40819014906883,
    "score_high": 75.24281656234058,
    "mean_cost_usd_per_task": 2.362349413758389,
    "median_cost_usd_per_task": 2.1098912999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9fafa3956afdc304",
    "variant": "mini-swe-agent - gemini-3-8-flash (medium)",
    "score": 71.01769911504425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 68.73689454216633,
    "score_high": 73.29850368792218,
    "mean_cost_usd_per_task": 1.9671024789823006,
    "median_cost_usd_per_task": 1.7342966249999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c190b81e19d238cc",
    "variant": "Gemini 3.6 Flash (high)",
    "score": 33.9786,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ec826f6447a6ed8b",
    "variant": "Artificial Analysis - Gemini 3.6 Flash (high)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.6-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4b88e3c88227052e",
    "variant": "gemini-3.6-flash-high",
    "score": 1536,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1528.5,
    "score_high": 1543.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.6-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:ee3d29f57f6b6e33",
    "variant": "Gemini 3.6 Flash (High)",
    "score": -7.67,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -8.75,
    "score_high": -6.59,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.3,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_pro_us::gemini-3.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e1743e5569cb8648",
    "variant": "mini-swe-agent - gemini-3-6-flash (high)",
    "score": 46.68141592920354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 42.97656202995626,
    "score_high": 50.386269828450814,
    "mean_cost_usd_per_task": 4.419013277333334,
    "median_cost_usd_per_task": 3.444695325000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a795ed51d673418d",
    "variant": "Gemini 3.8 Flash (high)",
    "score": 40.9262,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8f226080bd0bde9a",
    "variant": "Gemini 3.8 Flash (medium)",
    "score": 39.774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e0b41460917d3eff",
    "variant": "Gemini 3.8 Flash (low)",
    "score": 33.4548,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:206ddf92cd474c5f",
    "variant": "mini-SWE-agent - Gemini 3.8 Flash (high)",
    "score": 19.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 15.73,
    "score_high": 22.45,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a1eae5d167a32a34",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (medium)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a0853cb96c8ece1",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (high)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:76b42aa2f87efd5c",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (low)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:cee78179b654f666",
    "variant": "gemini-3.8-flash-high",
    "score": 1583,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1575.1,
    "score_high": 1590.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:60a00778bc1492a5",
    "variant": "Gemini 3.8 Flash (High)",
    "score": 2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 2.14,
    "score_high": 3.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.58,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:68de21286728c605",
    "variant": "Antigravity SDK - Gemini 3.8 Flash (high)",
    "score": 41.8632,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Antigravity SDK v0.1.12",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.4674,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e5b1ca76e59dabd0",
    "variant": "Gemini 3.8 Flash",
    "score": 68.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.210201,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a4e0e06e8292b616",
    "variant": "mini-swe-agent - gemini-3-8-flash (high)",
    "score": 73.8255033557047,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 72.40819014906883,
    "score_high": 75.24281656234058,
    "mean_cost_usd_per_task": 2.362349413758389,
    "median_cost_usd_per_task": 2.1098912999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_5x_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9fafa3956afdc304",
    "variant": "mini-swe-agent - gemini-3-8-flash (medium)",
    "score": 71.01769911504425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 68.73689454216633,
    "score_high": 73.29850368792218,
    "mean_cost_usd_per_task": 1.9671024789823006,
    "median_cost_usd_per_task": 1.7342966249999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a795ed51d673418d",
    "variant": "Gemini 3.8 Flash (high)",
    "score": 40.9262,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8f226080bd0bde9a",
    "variant": "Gemini 3.8 Flash (medium)",
    "score": 39.774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e0b41460917d3eff",
    "variant": "Gemini 3.8 Flash (low)",
    "score": 33.4548,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:206ddf92cd474c5f",
    "variant": "mini-SWE-agent - Gemini 3.8 Flash (high)",
    "score": 19.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 15.73,
    "score_high": 22.45,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a1eae5d167a32a34",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (medium)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a0853cb96c8ece1",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (high)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:76b42aa2f87efd5c",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (low)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:cee78179b654f666",
    "variant": "gemini-3.8-flash-high",
    "score": 1583,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1575.1,
    "score_high": 1590.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:60a00778bc1492a5",
    "variant": "Gemini 3.8 Flash (High)",
    "score": 2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 2.14,
    "score_high": 3.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.58,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:68de21286728c605",
    "variant": "Antigravity SDK - Gemini 3.8 Flash (high)",
    "score": 41.8632,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Antigravity SDK v0.1.12",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.4674,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e5b1ca76e59dabd0",
    "variant": "Gemini 3.8 Flash",
    "score": 68.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.210201,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a4e0e06e8292b616",
    "variant": "mini-swe-agent - gemini-3-8-flash (high)",
    "score": 73.8255033557047,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 72.40819014906883,
    "score_high": 75.24281656234058,
    "mean_cost_usd_per_task": 2.362349413758389,
    "median_cost_usd_per_task": 2.1098912999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "google_ai_ultra_20x_us::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9fafa3956afdc304",
    "variant": "mini-swe-agent - gemini-3-8-flash (medium)",
    "score": 71.01769911504425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 68.73689454216633,
    "score_high": 73.29850368792218,
    "mean_cost_usd_per_task": 1.9671024789823006,
    "median_cost_usd_per_task": 1.7342966249999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:68425237e9876779",
    "variant": "Claude Opus 5 (max)",
    "score": 50.7771,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a154cb4e9c99189",
    "variant": "Claude Opus 5 (xhigh)",
    "score": 49.6774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:295f5f7bdfa8d248",
    "variant": "Claude Opus 5 (high)",
    "score": 48.1219,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bacfec5f5f91d13c",
    "variant": "Claude Opus 5 (medium)",
    "score": 44.8253,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e42133cf9100a842",
    "variant": "Claude Opus 5 (low)",
    "score": 39.3543,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7d59ed14e6a26f29",
    "variant": "Claude Code - Opus 5 (xhigh)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.769999999999996,
    "score_high": 57.11,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cec3b7db483cca26",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 51.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 48.43,
    "score_high": 55.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:82e30cded058a067",
    "variant": "Claude Code - Opus 5 (high)",
    "score": 50.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 46.57,
    "score_high": 54.029999999999994,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:314e4521dd78b2f2",
    "variant": "Claude Code - Opus 5 (medium)",
    "score": 44.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 41.02,
    "score_high": 48.68,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:3ef9fcfb65e0cb76",
    "variant": "Claude Code - Opus 5 (low)",
    "score": 34.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 30.91,
    "score_high": 38.79,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ed48e92962897a4",
    "variant": "Artificial Analysis - Claude Opus 5 (max)",
    "score": 48.9899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0838ca37e5fa42da",
    "variant": "Artificial Analysis - Claude Opus 5 (xhigh)",
    "score": 46.4646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8e10956f03aaa14d",
    "variant": "Artificial Analysis - Claude Opus 5 (high)",
    "score": 45.9596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:314fe657e048e298",
    "variant": "Artificial Analysis - Claude Opus 5 (medium)",
    "score": 34.3434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a61fb5355f7888c8",
    "variant": "Artificial Analysis - Claude Opus 5 (low)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:3aa3e36faa602970",
    "variant": "claude-opus-5-max",
    "score": 1694,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1687.5,
    "score_high": 1700.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:6b8714542169429d",
    "variant": "claude-opus-5-high",
    "score": 1660,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1654.3,
    "score_high": 1665.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:63ab115851e0de58",
    "variant": "Claude Opus 5 (High)",
    "score": 8.76,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.26,
    "score_high": 10.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.5,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:7b426212aba5971e",
    "variant": "Claude Opus 5 (Max)",
    "score": 8.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 6.98,
    "score_high": 10.120000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 3.59,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:e0b71dfaa4f1714e",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 59.7264,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 10.7892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f029cafdaf0a4ee3",
    "variant": "mini-swe-agent - claude-opus-5 (max)",
    "score": 73.64864864864865,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.77633822227692,
    "score_high": 77.52095907502039,
    "mean_cost_usd_per_task": 11.837583271396396,
    "median_cost_usd_per_task": 10.4281505,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:853cb17f0e600556",
    "variant": "mini-swe-agent - claude-opus-5 (xhigh)",
    "score": 73.15436241610739,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 70.09338059446893,
    "score_high": 76.21534423774585,
    "mean_cost_usd_per_task": 9.07220232326622,
    "median_cost_usd_per_task": 7.928816750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e252d58fa6da2ebe",
    "variant": "mini-swe-agent - claude-opus-5 (high)",
    "score": 72.82850779510022,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 70.88307563794007,
    "score_high": 74.77393995226038,
    "mean_cost_usd_per_task": 6.076084489977728,
    "median_cost_usd_per_task": 4.96882375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:df5db3bddc1856ee",
    "variant": "mini-swe-agent - claude-opus-5 (medium)",
    "score": 68.90380313199105,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 67.73124446609795,
    "score_high": 70.07636179788415,
    "mean_cost_usd_per_task": 3.28978764541387,
    "median_cost_usd_per_task": 2.4819885000000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3353f4eaaecc0e42",
    "variant": "mini-swe-agent - claude-opus-5 (low)",
    "score": 58.12917594654788,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 55.79848799986361,
    "score_high": 60.45986389323216,
    "mean_cost_usd_per_task": 1.6626223919821828,
    "median_cost_usd_per_task": 1.2162672499999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:68425237e9876779",
    "variant": "Claude Opus 5 (max)",
    "score": 50.7771,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a154cb4e9c99189",
    "variant": "Claude Opus 5 (xhigh)",
    "score": 49.6774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:295f5f7bdfa8d248",
    "variant": "Claude Opus 5 (high)",
    "score": 48.1219,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bacfec5f5f91d13c",
    "variant": "Claude Opus 5 (medium)",
    "score": 44.8253,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e42133cf9100a842",
    "variant": "Claude Opus 5 (low)",
    "score": 39.3543,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7d59ed14e6a26f29",
    "variant": "Claude Code - Opus 5 (xhigh)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.769999999999996,
    "score_high": 57.11,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cec3b7db483cca26",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 51.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 48.43,
    "score_high": 55.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:82e30cded058a067",
    "variant": "Claude Code - Opus 5 (high)",
    "score": 50.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 46.57,
    "score_high": 54.029999999999994,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:314e4521dd78b2f2",
    "variant": "Claude Code - Opus 5 (medium)",
    "score": 44.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 41.02,
    "score_high": 48.68,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:3ef9fcfb65e0cb76",
    "variant": "Claude Code - Opus 5 (low)",
    "score": 34.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 30.91,
    "score_high": 38.79,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ed48e92962897a4",
    "variant": "Artificial Analysis - Claude Opus 5 (max)",
    "score": 48.9899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0838ca37e5fa42da",
    "variant": "Artificial Analysis - Claude Opus 5 (xhigh)",
    "score": 46.4646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8e10956f03aaa14d",
    "variant": "Artificial Analysis - Claude Opus 5 (high)",
    "score": 45.9596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:314fe657e048e298",
    "variant": "Artificial Analysis - Claude Opus 5 (medium)",
    "score": 34.3434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a61fb5355f7888c8",
    "variant": "Artificial Analysis - Claude Opus 5 (low)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:3aa3e36faa602970",
    "variant": "claude-opus-5-max",
    "score": 1694,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1687.5,
    "score_high": 1700.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:6b8714542169429d",
    "variant": "claude-opus-5-high",
    "score": 1660,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1654.3,
    "score_high": 1665.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:63ab115851e0de58",
    "variant": "Claude Opus 5 (High)",
    "score": 8.76,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.26,
    "score_high": 10.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.5,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:7b426212aba5971e",
    "variant": "Claude Opus 5 (Max)",
    "score": 8.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 6.98,
    "score_high": 10.120000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 3.59,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:e0b71dfaa4f1714e",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 59.7264,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 10.7892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f029cafdaf0a4ee3",
    "variant": "mini-swe-agent - claude-opus-5 (max)",
    "score": 73.64864864864865,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.77633822227692,
    "score_high": 77.52095907502039,
    "mean_cost_usd_per_task": 11.837583271396396,
    "median_cost_usd_per_task": 10.4281505,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:853cb17f0e600556",
    "variant": "mini-swe-agent - claude-opus-5 (xhigh)",
    "score": 73.15436241610739,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 70.09338059446893,
    "score_high": 76.21534423774585,
    "mean_cost_usd_per_task": 9.07220232326622,
    "median_cost_usd_per_task": 7.928816750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e252d58fa6da2ebe",
    "variant": "mini-swe-agent - claude-opus-5 (high)",
    "score": 72.82850779510022,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 70.88307563794007,
    "score_high": 74.77393995226038,
    "mean_cost_usd_per_task": 6.076084489977728,
    "median_cost_usd_per_task": 4.96882375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:df5db3bddc1856ee",
    "variant": "mini-swe-agent - claude-opus-5 (medium)",
    "score": 68.90380313199105,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 67.73124446609795,
    "score_high": 70.07636179788415,
    "mean_cost_usd_per_task": 3.28978764541387,
    "median_cost_usd_per_task": 2.4819885000000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3353f4eaaecc0e42",
    "variant": "mini-swe-agent - claude-opus-5 (low)",
    "score": 58.12917594654788,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 55.79848799986361,
    "score_high": 60.45986389323216,
    "mean_cost_usd_per_task": 1.6626223919821828,
    "median_cost_usd_per_task": 1.2162672499999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:68425237e9876779",
    "variant": "Claude Opus 5 (max)",
    "score": 50.7771,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a154cb4e9c99189",
    "variant": "Claude Opus 5 (xhigh)",
    "score": 49.6774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:295f5f7bdfa8d248",
    "variant": "Claude Opus 5 (high)",
    "score": 48.1219,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bacfec5f5f91d13c",
    "variant": "Claude Opus 5 (medium)",
    "score": 44.8253,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e42133cf9100a842",
    "variant": "Claude Opus 5 (low)",
    "score": 39.3543,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7d59ed14e6a26f29",
    "variant": "Claude Code - Opus 5 (xhigh)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.769999999999996,
    "score_high": 57.11,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cec3b7db483cca26",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 51.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 48.43,
    "score_high": 55.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:82e30cded058a067",
    "variant": "Claude Code - Opus 5 (high)",
    "score": 50.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 46.57,
    "score_high": 54.029999999999994,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:314e4521dd78b2f2",
    "variant": "Claude Code - Opus 5 (medium)",
    "score": 44.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 41.02,
    "score_high": 48.68,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:3ef9fcfb65e0cb76",
    "variant": "Claude Code - Opus 5 (low)",
    "score": 34.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 30.91,
    "score_high": 38.79,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ed48e92962897a4",
    "variant": "Artificial Analysis - Claude Opus 5 (max)",
    "score": 48.9899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0838ca37e5fa42da",
    "variant": "Artificial Analysis - Claude Opus 5 (xhigh)",
    "score": 46.4646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8e10956f03aaa14d",
    "variant": "Artificial Analysis - Claude Opus 5 (high)",
    "score": 45.9596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:314fe657e048e298",
    "variant": "Artificial Analysis - Claude Opus 5 (medium)",
    "score": 34.3434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a61fb5355f7888c8",
    "variant": "Artificial Analysis - Claude Opus 5 (low)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:3aa3e36faa602970",
    "variant": "claude-opus-5-max",
    "score": 1694,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1687.5,
    "score_high": 1700.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:6b8714542169429d",
    "variant": "claude-opus-5-high",
    "score": 1660,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1654.3,
    "score_high": 1665.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:63ab115851e0de58",
    "variant": "Claude Opus 5 (High)",
    "score": 8.76,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.26,
    "score_high": 10.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.5,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:7b426212aba5971e",
    "variant": "Claude Opus 5 (Max)",
    "score": 8.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 6.98,
    "score_high": 10.120000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 3.59,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:e0b71dfaa4f1714e",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 59.7264,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 10.7892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f029cafdaf0a4ee3",
    "variant": "mini-swe-agent - claude-opus-5 (max)",
    "score": 73.64864864864865,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.77633822227692,
    "score_high": 77.52095907502039,
    "mean_cost_usd_per_task": 11.837583271396396,
    "median_cost_usd_per_task": 10.4281505,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:853cb17f0e600556",
    "variant": "mini-swe-agent - claude-opus-5 (xhigh)",
    "score": 73.15436241610739,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 70.09338059446893,
    "score_high": 76.21534423774585,
    "mean_cost_usd_per_task": 9.07220232326622,
    "median_cost_usd_per_task": 7.928816750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e252d58fa6da2ebe",
    "variant": "mini-swe-agent - claude-opus-5 (high)",
    "score": 72.82850779510022,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 70.88307563794007,
    "score_high": 74.77393995226038,
    "mean_cost_usd_per_task": 6.076084489977728,
    "median_cost_usd_per_task": 4.96882375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:df5db3bddc1856ee",
    "variant": "mini-swe-agent - claude-opus-5 (medium)",
    "score": 68.90380313199105,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 67.73124446609795,
    "score_high": 70.07636179788415,
    "mean_cost_usd_per_task": 3.28978764541387,
    "median_cost_usd_per_task": 2.4819885000000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3353f4eaaecc0e42",
    "variant": "mini-swe-agent - claude-opus-5 (low)",
    "score": 58.12917594654788,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 55.79848799986361,
    "score_high": 60.45986389323216,
    "mean_cost_usd_per_task": 1.6626223919821828,
    "median_cost_usd_per_task": 1.2162672499999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:71823637d973a0fc",
    "variant": "Claude Fable 5.1 (max with fallback)",
    "score": 53.3549,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3f66aafbb8812925",
    "variant": "Claude Fable 5.1 (xhigh with fallback)",
    "score": 53.2033,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:74265ef58fb6e45b",
    "variant": "Claude Fable 5.1 (high with fallback)",
    "score": 51.1516,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9a927f4404e32355",
    "variant": "Claude Fable 5.1 (medium with fallback)",
    "score": 48.9206,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ceeec877967a38a",
    "variant": "Claude Fable 5.1 (low with fallback)",
    "score": 46.8163,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:136537b36ce98c25",
    "variant": "Claude Code - Fable 5.1 (max)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.120000000000005,
    "score_high": 61.64,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cc67912665adccef",
    "variant": "Claude Code - Fable 5.1 (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.52,
    "score_high": 61.24,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:c1be8fa31509c696",
    "variant": "Claude Code - Fable 5.1 (high)",
    "score": 54.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.11,
    "score_high": 57.989999999999995,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5edd3a6853cd6339",
    "variant": "Claude Code - Fable 5.1 (medium)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 50.55,
    "score_high": 57.33,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4bcb6aba27442f07",
    "variant": "Claude Code - Fable 5.1 (low)",
    "score": 43.33,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.72,
    "score_high": 46.94,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:41e12ce515ec9121",
    "variant": "Artificial Analysis - Claude Fable 5.1 (xhigh with fallback)",
    "score": 55.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1512d68b0eb6bc1b",
    "variant": "Artificial Analysis - Claude Fable 5.1 (max with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e606b01ceda846f9",
    "variant": "Artificial Analysis - Claude Fable 5.1 (high with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:93ccfc6e6c1f4910",
    "variant": "Artificial Analysis - Claude Fable 5.1 (medium with fallback)",
    "score": 44.9495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5e01b08628a88aac",
    "variant": "Artificial Analysis - Claude Fable 5.1 (low with fallback)",
    "score": 40.404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:8e70472a84bf71d1",
    "variant": "claude-fable-5.1-max",
    "score": 1751,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1741.3,
    "score_high": 1760.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:d1cdd70383ae2039",
    "variant": "Claude Fable 5.1 (Max)",
    "score": 14.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 12.63,
    "score_high": 16.47,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 4.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:f882189259104e87",
    "variant": "Claude Code - Fable 5.1 (max) (with fallback)",
    "score": 62.2225,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 12.3881,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1041b2cdd9886064",
    "variant": "Devin Fusion CLI - Claude Fable 5.1 XHigh + SWE-2 Medium",
    "score": 61.6826,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.8971,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5.1",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:0ed675e0b61ae3ac",
    "variant": "Claude Fable 5.1",
    "score": 80.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.660199,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_team::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_lite::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_plus::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra_fast::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_pro_plus::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegretto_cn::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_moderato_cn::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_andante_cn::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_andante_cn::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_andante_cn::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_andante_cn::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "kimi_allegro_cn::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_new_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_lite_cn_old_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_new_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_pro_cn_old_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_new_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_peak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_mid::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "glm_coding_max_cn_old_offpeak::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_cn::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_cn::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_cn::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_cn::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_cn::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_cn::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_cn::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_cn::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_global::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_global::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_global::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_max_global::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_global::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_global::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_global::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_ultra_global::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_cn::qwen3.7-plus",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e94df38c6b223ca",
    "variant": "Qwen3.7 Plus",
    "score": 25.1622,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_cn::qwen3.7-plus",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d9d54fa83beecde",
    "variant": "Artificial Analysis - Qwen3.7 Plus",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_cn::qwen3.7-plus",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9cf4eb892a450683",
    "variant": "Qwen3.7 Plus",
    "score": -7.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.75,
    "score_high": -5.8100000000000005,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_global::qwen3.7-plus",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e94df38c6b223ca",
    "variant": "Qwen3.7 Plus",
    "score": 25.1622,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_global::qwen3.7-plus",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d9d54fa83beecde",
    "variant": "Artificial Analysis - Qwen3.7 Plus",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "aliyun_coding_pro_global::qwen3.7-plus",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9cf4eb892a450683",
    "variant": "Qwen3.7 Plus",
    "score": -7.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.75,
    "score_high": -5.8100000000000005,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e41e4b6709da24d4",
    "variant": "GPT-6 Luna (max)",
    "score": 37.256,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:711bafc42ade2516",
    "variant": "GPT-6 Luna (xhigh)",
    "score": 33.8846,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:927f29d66e09bcc0",
    "variant": "GPT-6 Luna (high)",
    "score": 32.1482,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:51051c5b6fc81a75",
    "variant": "GPT-6 Luna (medium)",
    "score": 29.462,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9e4a1080bc5cdeda",
    "variant": "GPT-6 Luna (low)",
    "score": 20.9225,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be701ec71aacde7a",
    "variant": "GPT-6 Luna (non-reasoning)",
    "score": 18.2617,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4d4153eb38f2e84f",
    "variant": "Artificial Analysis - GPT-6 Luna (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3956f4765e345bfa",
    "variant": "Artificial Analysis - GPT-6 Luna (xhigh)",
    "score": 8.0808,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:964384bb8d3b9a13",
    "variant": "Artificial Analysis - GPT-6 Luna (high)",
    "score": 4.5455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:62b32b0accfdc3e1",
    "variant": "Artificial Analysis - GPT-6 Luna (medium)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c911fafd76fe1373",
    "variant": "Artificial Analysis - GPT-6 Luna (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1f723b35d187e5ec",
    "variant": "Artificial Analysis - GPT-6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:27376aa104f48f0e",
    "variant": "gpt-6-luna-max",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1573.0,
    "score_high": 1591.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:04bd9ba65c143398",
    "variant": "GPT 6 Luna (Max)",
    "score": 1.68,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 0.27,
    "score_high": 3.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.06,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:01e2ffcaa1665576",
    "variant": "Codex - GPT-6 Luna (max)",
    "score": 41.0744,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.1759,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::gpt-6-luna",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:df380d7af56a8dd0",
    "variant": "GPT-6 Luna",
    "score": 83.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.015871,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4b9229f7a5210ab7",
    "variant": "GLM-5.2 (max)",
    "score": 33.7055,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bf6c2c604a56c9d0",
    "variant": "GLM-5.2 (non-reasoning) [AA estimate]",
    "score": 22.4323,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9ad8c75e6b68658f",
    "variant": "Artificial Analysis - GLM-5.2 (max)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "arena_code",
    "configuration_id": "arena_code:828ee7654a1873aa",
    "variant": "glm-5.2-max",
    "score": 1605,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1598.6,
    "score_high": 1611.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f4f60f98940c49ee",
    "variant": "GLM 5.2 (Max)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.9000000000000004,
    "score_high": 4.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.76,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3c0de09601f2c8a8",
    "variant": "mini-swe-agent - glm-5-2 (max)",
    "score": 43.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 42.05214815719697,
    "score_high": 45.50340739835859,
    "mean_cost_usd_per_task": 3.9199075743111114,
    "median_cost_usd_per_task": 3.4637479200000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:71a3c9c8333b9bfd",
    "variant": "mini-swe-agent - glm-5-2 (high)",
    "score": 36.283185840707965,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 31.533112892786306,
    "score_high": 41.033258788629624,
    "mean_cost_usd_per_task": 2.8355164725663715,
    "median_cost_usd_per_task": 2.25012998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:97c970284455bffa",
    "variant": "Kimi K2.6",
    "score": 26.9792,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be58b1c3ec11fb7d",
    "variant": "Kimi K2.6 (non-reasoning) [AA estimate]",
    "score": 23.5696,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ca3671e92d985c3e",
    "variant": "Artificial Analysis - Kimi K2.6",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::kimi-k2.6",
    "board": "arena_code",
    "configuration_id": "arena_code:b806900ce18f190d",
    "variant": "kimi-k2.6",
    "score": 1509,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1501.8,
    "score_high": 1516.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::longcat-2.0",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:73481783e67e2f5b",
    "variant": "LongCat 2.0",
    "score": 19.1123,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::longcat-2.0",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:d0a6a751fe4ac57c",
    "variant": "Artificial Analysis - LongCat 2.0",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8919405f90e7565f",
    "variant": "Qwen3.8 Max",
    "score": 40.1529,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0487a0a408dccb82",
    "variant": "Artificial Analysis - Qwen3.8 Max",
    "score": 18.6869,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "arena_code",
    "configuration_id": "arena_code:ab7cf4e12f67d532",
    "variant": "qwen3.8-max",
    "score": 1671,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1659.0,
    "score_high": 1683.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9ce366a4c245bae4",
    "variant": "Qwen3.8 Max",
    "score": 2.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.15,
    "score_high": 3.4499999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:82bc37b4bd5aa375",
    "variant": "Claude Code - Qwen3.8 Max",
    "score": 43.2653,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.479,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:fbd3d33fa1d7cf9a",
    "variant": "Qwen 3.8-Max",
    "score": 72,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.595399,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.8-max",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f20515f2e81cba89",
    "variant": "mini-swe-agent - qwen3-8-max (xhigh)",
    "score": 57.46102449888642,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.798231826378874,
    "score_high": 60.12381717139396,
    "mean_cost_usd_per_task": 3.7290646500445437,
    "median_cost_usd_per_task": 3.132689060000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.7-plus",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e94df38c6b223ca",
    "variant": "Qwen3.7 Plus",
    "score": 25.1622,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.7-plus",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d9d54fa83beecde",
    "variant": "Artificial Analysis - Qwen3.7 Plus",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::qwen3.7-plus",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9cf4eb892a450683",
    "variant": "Qwen3.7 Plus",
    "score": -7.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.75,
    "score_high": -5.8100000000000005,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash-vision-exp",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ab3fed6fb264856",
    "variant": "DeepSeek V4 Flash Vision (max)",
    "score": 34.8391,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::deepseek-v4-flash-vision-exp",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2bd2f5c3a28cefaa",
    "variant": "Artificial Analysis - DeepSeek V4 Flash Vision (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy4-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:a9cb90573e973a11",
    "variant": "hy4-preview",
    "score": 1633,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1623.6,
    "score_high": 1642.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy4-preview",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:edee122a50e59a89",
    "variant": "Hy4 preview",
    "score": 4.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 3.39,
    "score_high": 5.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.29,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy4-preview",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:1d059a6d807d4308",
    "variant": "Hunyuan H4 Preview",
    "score": 74.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.417793,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:131d42e954c0324c",
    "variant": "Hy3",
    "score": 25.2973,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7e5e9735030b01c8",
    "variant": "Artificial Analysis - Hy3",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy3",
    "board": "arena_code",
    "configuration_id": "arena_code:c23c1b85207e0226",
    "variant": "hy3",
    "score": 1508,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1499.3,
    "score_high": 1516.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "opencode_go::hy3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3a37aca313fcd27d",
    "variant": "Hy3",
    "score": -5.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -6.93,
    "score_high": -4.470000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4b9229f7a5210ab7",
    "variant": "GLM-5.2 (max)",
    "score": 33.7055,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bf6c2c604a56c9d0",
    "variant": "GLM-5.2 (non-reasoning) [AA estimate]",
    "score": 22.4323,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9ad8c75e6b68658f",
    "variant": "Artificial Analysis - GLM-5.2 (max)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "arena_code",
    "configuration_id": "arena_code:828ee7654a1873aa",
    "variant": "glm-5.2-max",
    "score": 1605,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1598.6,
    "score_high": 1611.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f4f60f98940c49ee",
    "variant": "GLM 5.2 (Max)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.9000000000000004,
    "score_high": 4.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.76,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3c0de09601f2c8a8",
    "variant": "mini-swe-agent - glm-5-2 (max)",
    "score": 43.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 42.05214815719697,
    "score_high": 45.50340739835859,
    "mean_cost_usd_per_task": 3.9199075743111114,
    "median_cost_usd_per_task": 3.4637479200000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:71a3c9c8333b9bfd",
    "variant": "mini-swe-agent - glm-5-2 (high)",
    "score": 36.283185840707965,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 31.533112892786306,
    "score_high": 41.033258788629624,
    "mean_cost_usd_per_task": 2.8355164725663715,
    "median_cost_usd_per_task": 2.25012998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:131d42e954c0324c",
    "variant": "Hy3",
    "score": 25.2973,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7e5e9735030b01c8",
    "variant": "Artificial Analysis - Hy3",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy3",
    "board": "arena_code",
    "configuration_id": "arena_code:c23c1b85207e0226",
    "variant": "hy3",
    "score": 1508,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1499.3,
    "score_high": 1516.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3a37aca313fcd27d",
    "variant": "Hy3",
    "score": -5.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -6.93,
    "score_high": -4.470000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4555232c8e387389",
    "variant": "Qwen3.8 27B (xhigh)",
    "score": 33.6963,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:386e5826aefad337",
    "variant": "Qwen3.8 27B (medium)",
    "score": 27.5508,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d136741f62069cb1",
    "variant": "Qwen3.8 27B (low)",
    "score": 26.2048,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7bed7be52e30496d",
    "variant": "Qwen3.8 27B (non-reasoning)",
    "score": 20.1502,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c563447fe73f34f6",
    "variant": "Artificial Analysis - Qwen3.8 27B (xhigh)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:d9a51d09614610e8",
    "variant": "Artificial Analysis - Qwen3.8 27B (medium)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a025952071adf945",
    "variant": "Artificial Analysis - Qwen3.8 27B (low)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7f4fd5ee28b042c6",
    "variant": "Artificial Analysis - Qwen3.8 27B (non-reasoning)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "arena_code",
    "configuration_id": "arena_code:b8dc0ef18e30c1dc",
    "variant": "qwen3.8-27b",
    "score": 1590,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1583.0,
    "score_high": 1597.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-27b",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:22652d46f50fe772",
    "variant": "Qwen 3.8 27B",
    "score": -1.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -2.21,
    "score_high": -1.0100000000000002,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.31,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a795ed51d673418d",
    "variant": "Gemini 3.8 Flash (high)",
    "score": 40.9262,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8f226080bd0bde9a",
    "variant": "Gemini 3.8 Flash (medium)",
    "score": 39.774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e0b41460917d3eff",
    "variant": "Gemini 3.8 Flash (low)",
    "score": 33.4548,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:206ddf92cd474c5f",
    "variant": "mini-SWE-agent - Gemini 3.8 Flash (high)",
    "score": 19.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 15.73,
    "score_high": 22.45,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a1eae5d167a32a34",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (medium)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a0853cb96c8ece1",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (high)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:76b42aa2f87efd5c",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (low)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:cee78179b654f666",
    "variant": "gemini-3.8-flash-high",
    "score": 1583,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1575.1,
    "score_high": 1590.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:60a00778bc1492a5",
    "variant": "Gemini 3.8 Flash (High)",
    "score": 2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 2.14,
    "score_high": 3.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.58,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:68de21286728c605",
    "variant": "Antigravity SDK - Gemini 3.8 Flash (high)",
    "score": 41.8632,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Antigravity SDK v0.1.12",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.4674,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e5b1ca76e59dabd0",
    "variant": "Gemini 3.8 Flash",
    "score": 68.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.210201,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a4e0e06e8292b616",
    "variant": "mini-swe-agent - gemini-3-8-flash (high)",
    "score": 73.8255033557047,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 72.40819014906883,
    "score_high": 75.24281656234058,
    "mean_cost_usd_per_task": 2.362349413758389,
    "median_cost_usd_per_task": 2.1098912999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9fafa3956afdc304",
    "variant": "mini-swe-agent - gemini-3-8-flash (medium)",
    "score": 71.01769911504425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 68.73689454216633,
    "score_high": 73.29850368792218,
    "mean_cost_usd_per_task": 1.9671024789823006,
    "median_cost_usd_per_task": 1.7342966249999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-max",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b3246639fa93a057",
    "variant": "Qwen3.7 Max",
    "score": 29.4572,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-max",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a3c02275461ec0cb",
    "variant": "Artificial Analysis - Qwen3.7 Max",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-max",
    "board": "arena_code",
    "configuration_id": "arena_code:ab16d803c029884c",
    "variant": "qwen3.7-max-20260517",
    "score": 1515,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1507.6,
    "score_high": 1522.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-max",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:15166add541e68d5",
    "variant": "Qwen3.7 Max",
    "score": -5.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": -6.140000000000001,
    "score_high": -4.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.19,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-plus",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e94df38c6b223ca",
    "variant": "Qwen3.7 Plus",
    "score": 25.1622,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-plus",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d9d54fa83beecde",
    "variant": "Artificial Analysis - Qwen3.7 Plus",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.7-plus",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9cf4eb892a450683",
    "variant": "Qwen3.7 Plus",
    "score": -7.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.75,
    "score_high": -5.8100000000000005,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.6-plus",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:238aba7e1b811926",
    "variant": "Qwen3.6 Plus [AA estimate]",
    "score": 27.0099,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.6-plus",
    "board": "arena_code",
    "configuration_id": "arena_code:b7e5e5b8df1a65a0",
    "variant": "qwen3.6-plus",
    "score": 1461,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1455.4,
    "score_high": 1466.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8919405f90e7565f",
    "variant": "Qwen3.8 Max",
    "score": 40.1529,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0487a0a408dccb82",
    "variant": "Artificial Analysis - Qwen3.8 Max",
    "score": 18.6869,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "arena_code",
    "configuration_id": "arena_code:ab7cf4e12f67d532",
    "variant": "qwen3.8-max",
    "score": 1671,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1659.0,
    "score_high": 1683.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9ce366a4c245bae4",
    "variant": "Qwen3.8 Max",
    "score": 2.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.15,
    "score_high": 3.4499999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:82bc37b4bd5aa375",
    "variant": "Claude Code - Qwen3.8 Max",
    "score": 43.2653,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.479,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:fbd3d33fa1d7cf9a",
    "variant": "Qwen 3.8-Max",
    "score": 72,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.595399,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f20515f2e81cba89",
    "variant": "mini-swe-agent - qwen3-8-max (xhigh)",
    "score": 57.46102449888642,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.798231826378874,
    "score_high": 60.12381717139396,
    "mean_cost_usd_per_task": 3.7290646500445437,
    "median_cost_usd_per_task": 3.132689060000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e41e4b6709da24d4",
    "variant": "GPT-6 Luna (max)",
    "score": 37.256,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:711bafc42ade2516",
    "variant": "GPT-6 Luna (xhigh)",
    "score": 33.8846,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:927f29d66e09bcc0",
    "variant": "GPT-6 Luna (high)",
    "score": 32.1482,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:51051c5b6fc81a75",
    "variant": "GPT-6 Luna (medium)",
    "score": 29.462,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9e4a1080bc5cdeda",
    "variant": "GPT-6 Luna (low)",
    "score": 20.9225,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be701ec71aacde7a",
    "variant": "GPT-6 Luna (non-reasoning)",
    "score": 18.2617,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4d4153eb38f2e84f",
    "variant": "Artificial Analysis - GPT-6 Luna (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3956f4765e345bfa",
    "variant": "Artificial Analysis - GPT-6 Luna (xhigh)",
    "score": 8.0808,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:964384bb8d3b9a13",
    "variant": "Artificial Analysis - GPT-6 Luna (high)",
    "score": 4.5455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:62b32b0accfdc3e1",
    "variant": "Artificial Analysis - GPT-6 Luna (medium)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c911fafd76fe1373",
    "variant": "Artificial Analysis - GPT-6 Luna (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1f723b35d187e5ec",
    "variant": "Artificial Analysis - GPT-6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:27376aa104f48f0e",
    "variant": "gpt-6-luna-max",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1573.0,
    "score_high": 1591.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:04bd9ba65c143398",
    "variant": "GPT 6 Luna (Max)",
    "score": 1.68,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 0.27,
    "score_high": 3.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.06,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:01e2ffcaa1665576",
    "variant": "Codex - GPT-6 Luna (max)",
    "score": 41.0744,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.1759,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gpt-6-luna",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:df380d7af56a8dd0",
    "variant": "GPT-6 Luna",
    "score": 83.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.015871,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max-0902",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c9c2272b5b7ddbdf",
    "variant": "Qwen3.8 Max (0902)",
    "score": 45.4152,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max-0902",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:696204be45eb44af",
    "variant": "Artificial Analysis - Qwen3.8 Max (0902)",
    "score": 38.8889,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.8-max-0902",
    "board": "arena_code",
    "configuration_id": "arena_code:8f7b0b66ed443b08",
    "variant": "qwen3.8-max-0902",
    "score": 1670,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1662.0,
    "score_high": 1678.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy4-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:a9cb90573e973a11",
    "variant": "hy4-preview",
    "score": 1633,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1623.6,
    "score_high": 1642.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy4-preview",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:edee122a50e59a89",
    "variant": "Hy4 preview",
    "score": 4.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 3.39,
    "score_high": 5.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.29,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::hy4-preview",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:1d059a6d807d4308",
    "variant": "Hunyuan H4 Preview",
    "score": 74.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.417793,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3-flashx",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e7590d5e99a8809f",
    "variant": "GLM-5.3 Flash-X",
    "score": 80.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.097833,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash-vision-exp",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ab3fed6fb264856",
    "variant": "DeepSeek V4 Flash Vision (max)",
    "score": 34.8391,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::deepseek-v4-flash-vision-exp",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2bd2f5c3a28cefaa",
    "variant": "Artificial Analysis - DeepSeek V4 Flash Vision (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a8c28362dff3aa31",
    "variant": "Muse Spark 1.3 (max)",
    "score": 48.0923,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:eaee770ce12a30df",
    "variant": "Muse Spark 1.3 (xhigh)",
    "score": 45.0733,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3ceb10cebdd638c2",
    "variant": "Artificial Analysis - Muse Spark 1.3 (max)",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:77d9a42a8772a37d",
    "variant": "Artificial Analysis - Muse Spark 1.3 (xhigh)",
    "score": 16.6667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "arena_code",
    "configuration_id": "arena_code:d79805eb17b0ddce",
    "variant": "muse-spark-1.3-max",
    "score": 1655,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1646.3,
    "score_high": 1663.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "arena_code",
    "configuration_id": "arena_code:795cc8453d3a1a24",
    "variant": "muse-spark-1.3 (xHigh)",
    "score": 1623,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1614.2,
    "score_high": 1631.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0d8b2c85e74d262f",
    "variant": "Muse Spark 1.3 (Max)",
    "score": 4.19,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.6000000000000005,
    "score_high": 4.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.41,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:36a45d40bcfc3714",
    "variant": "Muse Code - Muse Spark 1.3 (max)",
    "score": 54.3027,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Muse Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.9775,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:2aeda79a0ee5dba5",
    "variant": "Muse Code - Muse Spark 1.3 (xhigh)",
    "score": 48.2993,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Muse Code 1.0.2 RC",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.4678,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:3d2b13f88b32b8ff",
    "variant": "Muse Spark 1.3",
    "score": 66.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.267309,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9666106dbc0fffc1",
    "variant": "Muse Spark 1.2 (xhigh)",
    "score": 39.5759,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:af37ce7e1e85aaba",
    "variant": "Artificial Analysis - Muse Spark 1.2 (xhigh)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.2",
    "board": "arena_code",
    "configuration_id": "arena_code:11c91ee348aca987",
    "variant": "muse-spark-1.2 (xHigh)",
    "score": 1532,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1518.4,
    "score_high": 1545.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:84c2affbfb9336da",
    "variant": "Muse Spark 1.2 (xHigh)",
    "score": -2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -3.65,
    "score_high": -2.27,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.4,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::muse-spark-1.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c181f2262d3e9d70",
    "variant": "mini-swe-agent - muse-spark-1-2 (xhigh)",
    "score": 54.86725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 52.74295943524101,
    "score_high": 56.99155383909527,
    "mean_cost_usd_per_task": 3.6955048180309733,
    "median_cost_usd_per_task": 2.6840506,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:829ff4209a0293bc",
    "variant": "Grok 4.5 (high)",
    "score": 38.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:98d088ff379b956d",
    "variant": "Grok Build - Grok 4.5 (high)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 9.8,
    "score_high": 15.04,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:68bfb23c4047a7a3",
    "variant": "Artificial Analysis - Grok 4.5 (high)",
    "score": 10.6061,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "arena_code",
    "configuration_id": "arena_code:dc0921a30ecddd2c",
    "variant": "grok-4.5",
    "score": 1552,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1545.4,
    "score_high": 1558.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:069dfce97d9ef41d",
    "variant": "Grok 4.5",
    "score": 1.11,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.1200000000000001,
    "score_high": 2.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:70b6e868fcb9cd80",
    "variant": "mini-swe-agent - grok-4-5 (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.48025737402474,
    "score_high": 56.04186651978057,
    "mean_cost_usd_per_task": 2.4157481725663716,
    "median_cost_usd_per_task": 2.02311,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:59269287bc1e95d8",
    "variant": "Gemini 3.7 Flash (medium) [AA estimate]",
    "score": 39.6178,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:aeabf6017dd74bc8",
    "variant": "Gemini 3.7 Flash (high)",
    "score": 39.0595,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cc014f66e9d183e0",
    "variant": "Gemini 3.7 Flash (low) [AA estimate]",
    "score": 36.9459,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2106790cd4627629",
    "variant": "mini-SWE-agent - Gemini 3.7 Flash (high)",
    "score": 11.21,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 8.760000000000002,
    "score_high": 13.66,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69dd3b76427af507",
    "variant": "Artificial Analysis - Gemini 3.7 Flash (high)",
    "score": 13.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:778f5c97eb827e03",
    "variant": "gemini-3.7-flash-high",
    "score": 1592,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1584.6,
    "score_high": 1599.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:47cad90e68374509",
    "variant": "Gemini 3.7 Flash (High)",
    "score": -1.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -2.4,
    "score_high": -0.8799999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e9d8d5305f3c7552",
    "variant": "mini-swe-agent - gemini-3-7-flash (medium)",
    "score": 65.48672566371681,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 62.40019338730129,
    "score_high": 68.57325794013234,
    "mean_cost_usd_per_task": 2.0251351826880533,
    "median_cost_usd_per_task": 1.65422055,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a62d7ab2cd07619d",
    "variant": "mini-swe-agent - gemini-3-7-flash (high)",
    "score": 65.2654867256637,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.47762421887939,
    "score_high": 67.05334923244803,
    "mean_cost_usd_per_task": 2.1762860351216813,
    "median_cost_usd_per_task": 1.9044440625,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c3c0d085a762f3d1",
    "variant": "mini-swe-agent - gemini-3-7-flash (low)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 51.171412865070785,
    "score_high": 56.35071102873452,
    "mean_cost_usd_per_task": 1.8322645629424779,
    "median_cost_usd_per_task": 1.3913454375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ae97bbe112769bcd",
    "variant": "Inkling (xhigh)",
    "score": 24.9848,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8b8fcc0fa14e07eb",
    "variant": "Artificial Analysis - Inkling (xhigh)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling",
    "board": "arena_code",
    "configuration_id": "arena_code:07b745ae2862d994",
    "variant": "inkling",
    "score": 1412,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1405.6,
    "score_high": 1418.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8967f33635820f8b",
    "variant": "Inkling",
    "score": -10.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -11.96,
    "score_high": -9.84,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.25,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling-small",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ecad05994d7b1af",
    "variant": "Inkling Small",
    "score": 25.6583,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling-small",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:d0b5249bef72ad97",
    "variant": "Artificial Analysis - Inkling Small",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling-small",
    "board": "arena_code",
    "configuration_id": "arena_code:5e9cc8edc5997bcf",
    "variant": "Inkling Small",
    "score": 1408,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1399.0,
    "score_high": 1417.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::inkling-small",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:03dbaa1180987af9",
    "variant": "Inkling Small",
    "score": -9.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -11.22,
    "score_high": -8.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-5-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fb0405a168316f85",
    "variant": "Step 5 Preview",
    "score": 43.7343,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-5-preview",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e7fa06d82cc14898",
    "variant": "Artificial Analysis - Step 5 Preview",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-5-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:5ebff85aa1280e1f",
    "variant": "step-5-preview-high",
    "score": 1570,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1556.8,
    "score_high": 1583.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e8828ee245d130af",
    "variant": "Step 3.7 Flash [AA estimate]",
    "score": 19.4813,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f4ecc0cb880e6a93",
    "variant": "Step 3.5 Flash 2603 [AA estimate]",
    "score": 16.9641,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:19396846e36b1f6e",
    "variant": "Step 3.5 Flash [AA estimate]",
    "score": 16.6169,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::nemotron-3-ultra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5cd72513bff7d4b7",
    "variant": "Nemotron 3 Ultra",
    "score": 22.9279,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::nemotron-3-ultra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d0d41d5c6a6aa9b",
    "variant": "Artificial Analysis - Nemotron 3 Ultra",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::longcat-2.0",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:73481783e67e2f5b",
    "variant": "LongCat 2.0",
    "score": 19.1123,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::longcat-2.0",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:d0a6a751fe4ac57c",
    "variant": "Artificial Analysis - LongCat 2.0",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:97c970284455bffa",
    "variant": "Kimi K2.6",
    "score": 26.9792,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be58b1c3ec11fb7d",
    "variant": "Kimi K2.6 (non-reasoning) [AA estimate]",
    "score": 23.5696,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ca3671e92d985c3e",
    "variant": "Artificial Analysis - Kimi K2.6",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.6",
    "board": "arena_code",
    "configuration_id": "arena_code:b806900ce18f190d",
    "variant": "kimi-k2.6",
    "score": 1509,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1501.8,
    "score_high": 1516.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:589e83427c9b8ab7",
    "variant": "Kimi K2.5 [AA estimate]",
    "score": 23.4585,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1afe01378404f2e7",
    "variant": "Kimi K2.5 (non-reasoning) [AA estimate]",
    "score": 19.4343,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:79ddd44617f3ec62",
    "variant": "kimi-k2.5-thinking",
    "score": 1436,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "thinking",
    "service_mode": null,
    "score_low": 1430.8,
    "score_high": 1441.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::kimi-k2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:cbe1c293dbc12cfd",
    "variant": "kimi-k2.5-instant",
    "score": 1404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1392.0,
    "score_high": 1416.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f45138a64ed521bd",
    "variant": "GLM-5.1",
    "score": 26.0586,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:18011484156b18b6",
    "variant": "GLM-5.1 (non-reasoning) [AA estimate]",
    "score": 24.2412,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:39ff8a3fc7a8b6c2",
    "variant": "Artificial Analysis - GLM-5.1",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:19874ad7a301d76d",
    "variant": "glm-5.1",
    "score": 1508,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1501.2,
    "score_high": 1514.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b5ff5400e6b8641a",
    "variant": "GLM-5 [AA estimate]",
    "score": 27.9112,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:81bcbed3fd5a66b9",
    "variant": "GLM-5 (non-reasoning) [AA estimate]",
    "score": 21.7826,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::glm-5",
    "board": "arena_code",
    "configuration_id": "arena_code:1744764b0671d723",
    "variant": "glm-5",
    "score": 1434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1425.9,
    "score_high": 1442.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.6-max-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a58445ae77253e4",
    "variant": "Qwen3.6 Max Preview [AA estimate]",
    "score": 28.3749,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::qwen3.6-max-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:efbac4e58b06eb10",
    "variant": "qwen3.6-max-preview",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1469.5,
    "score_high": 1494.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ae390fdc5fe89d6c",
    "variant": "MiniMax-M2.5 [AA estimate]",
    "score": 22.7966,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "command_code_goat::minimax-m2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:28d1b5355f79eb7b",
    "variant": "minimax-m2.5",
    "score": 1386,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1377.7,
    "score_high": 1394.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4b9229f7a5210ab7",
    "variant": "GLM-5.2 (max)",
    "score": 33.7055,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bf6c2c604a56c9d0",
    "variant": "GLM-5.2 (non-reasoning) [AA estimate]",
    "score": 22.4323,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9ad8c75e6b68658f",
    "variant": "Artificial Analysis - GLM-5.2 (max)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "arena_code",
    "configuration_id": "arena_code:828ee7654a1873aa",
    "variant": "glm-5.2-max",
    "score": 1605,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1598.6,
    "score_high": 1611.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f4f60f98940c49ee",
    "variant": "GLM 5.2 (Max)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.9000000000000004,
    "score_high": 4.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.76,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3c0de09601f2c8a8",
    "variant": "mini-swe-agent - glm-5-2 (max)",
    "score": 43.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 42.05214815719697,
    "score_high": 45.50340739835859,
    "mean_cost_usd_per_task": 3.9199075743111114,
    "median_cost_usd_per_task": 3.4637479200000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:71a3c9c8333b9bfd",
    "variant": "mini-swe-agent - glm-5-2 (high)",
    "score": 36.283185840707965,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 31.533112892786306,
    "score_high": 41.033258788629624,
    "mean_cost_usd_per_task": 2.8355164725663715,
    "median_cost_usd_per_task": 2.25012998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f45138a64ed521bd",
    "variant": "GLM-5.1",
    "score": 26.0586,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:18011484156b18b6",
    "variant": "GLM-5.1 (non-reasoning) [AA estimate]",
    "score": 24.2412,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:39ff8a3fc7a8b6c2",
    "variant": "Artificial Analysis - GLM-5.1",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::glm-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:19874ad7a301d76d",
    "variant": "glm-5.1",
    "score": 1508,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1501.2,
    "score_high": 1514.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_pro::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4b9229f7a5210ab7",
    "variant": "GLM-5.2 (max)",
    "score": 33.7055,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bf6c2c604a56c9d0",
    "variant": "GLM-5.2 (non-reasoning) [AA estimate]",
    "score": 22.4323,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9ad8c75e6b68658f",
    "variant": "Artificial Analysis - GLM-5.2 (max)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "arena_code",
    "configuration_id": "arena_code:828ee7654a1873aa",
    "variant": "glm-5.2-max",
    "score": 1605,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1598.6,
    "score_high": 1611.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f4f60f98940c49ee",
    "variant": "GLM 5.2 (Max)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.9000000000000004,
    "score_high": 4.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.76,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3c0de09601f2c8a8",
    "variant": "mini-swe-agent - glm-5-2 (max)",
    "score": 43.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 42.05214815719697,
    "score_high": 45.50340739835859,
    "mean_cost_usd_per_task": 3.9199075743111114,
    "median_cost_usd_per_task": 3.4637479200000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:71a3c9c8333b9bfd",
    "variant": "mini-swe-agent - glm-5-2 (high)",
    "score": 36.283185840707965,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 31.533112892786306,
    "score_high": 41.033258788629624,
    "mean_cost_usd_per_task": 2.8355164725663715,
    "median_cost_usd_per_task": 2.25012998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f45138a64ed521bd",
    "variant": "GLM-5.1",
    "score": 26.0586,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:18011484156b18b6",
    "variant": "GLM-5.1 (non-reasoning) [AA estimate]",
    "score": 24.2412,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:39ff8a3fc7a8b6c2",
    "variant": "Artificial Analysis - GLM-5.1",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::glm-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:19874ad7a301d76d",
    "variant": "glm-5.1",
    "score": 1508,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1501.2,
    "score_high": 1514.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k2.7-code",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b0c9eb24f253523d",
    "variant": "Kimi K2.7 Code",
    "score": 25.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k2.7-code",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c9067f00834590ba",
    "variant": "Artificial Analysis - Kimi K2.7 Code",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k2.7-code",
    "board": "arena_code",
    "configuration_id": "arena_code:24e3159d841ef7a4",
    "variant": "kimi-k2.7-code",
    "score": 1473,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1463.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::kimi-k2.7-code",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c25e237262636381",
    "variant": "mini-swe-agent - kimi-k2-7-code (None)",
    "score": 30.53097345132743,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "none",
    "service_mode": null,
    "score_low": 30.030271799081337,
    "score_high": 31.031675103573527,
    "mean_cost_usd_per_task": 2.815536243274336,
    "median_cost_usd_per_task": 2.1955079100000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "ollama_max::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f4ecc0cb880e6a93",
    "variant": "Step 3.5 Flash 2603 [AA estimate]",
    "score": 16.9641,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:19396846e36b1f6e",
    "variant": "Step 3.5 Flash [AA estimate]",
    "score": 16.6169,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e8828ee245d130af",
    "variant": "Step 3.7 Flash [AA estimate]",
    "score": 19.4813,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-5-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fb0405a168316f85",
    "variant": "Step 5 Preview",
    "score": 43.7343,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-5-preview",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e7fa06d82cc14898",
    "variant": "Artificial Analysis - Step 5 Preview",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_mini_cn::step-5-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:5ebff85aa1280e1f",
    "variant": "step-5-preview-high",
    "score": 1570,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1556.8,
    "score_high": 1583.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f4ecc0cb880e6a93",
    "variant": "Step 3.5 Flash 2603 [AA estimate]",
    "score": 16.9641,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:19396846e36b1f6e",
    "variant": "Step 3.5 Flash [AA estimate]",
    "score": 16.6169,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e8828ee245d130af",
    "variant": "Step 3.7 Flash [AA estimate]",
    "score": 19.4813,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-5-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fb0405a168316f85",
    "variant": "Step 5 Preview",
    "score": 43.7343,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-5-preview",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e7fa06d82cc14898",
    "variant": "Artificial Analysis - Step 5 Preview",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_plus_cn::step-5-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:5ebff85aa1280e1f",
    "variant": "step-5-preview-high",
    "score": 1570,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1556.8,
    "score_high": 1583.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f4ecc0cb880e6a93",
    "variant": "Step 3.5 Flash 2603 [AA estimate]",
    "score": 16.9641,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:19396846e36b1f6e",
    "variant": "Step 3.5 Flash [AA estimate]",
    "score": 16.6169,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e8828ee245d130af",
    "variant": "Step 3.7 Flash [AA estimate]",
    "score": 19.4813,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-5-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fb0405a168316f85",
    "variant": "Step 5 Preview",
    "score": 43.7343,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-5-preview",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e7fa06d82cc14898",
    "variant": "Artificial Analysis - Step 5 Preview",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_pro_cn::step-5-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:5ebff85aa1280e1f",
    "variant": "step-5-preview-high",
    "score": 1570,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1556.8,
    "score_high": 1583.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f4ecc0cb880e6a93",
    "variant": "Step 3.5 Flash 2603 [AA estimate]",
    "score": 16.9641,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-3.5-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:19396846e36b1f6e",
    "variant": "Step 3.5 Flash [AA estimate]",
    "score": 16.6169,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e8828ee245d130af",
    "variant": "Step 3.7 Flash [AA estimate]",
    "score": 19.4813,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-5-preview",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fb0405a168316f85",
    "variant": "Step 5 Preview",
    "score": 43.7343,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-5-preview",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e7fa06d82cc14898",
    "variant": "Artificial Analysis - Step 5 Preview",
    "score": 33.3333,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "stepfun_max_cn::step-5-preview",
    "board": "arena_code",
    "configuration_id": "arena_code:5ebff85aa1280e1f",
    "variant": "step-5-preview-high",
    "score": 1570,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1556.8,
    "score_high": 1583.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_day::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_lite_night::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_day::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_standard_night::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_day::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_pro_night::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c0536a98a4f2e51d",
    "variant": "MiMo-V2.5-Pro",
    "score": 25.9869,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:95331afc94452f27",
    "variant": "MiMo-V2.5-Pro (non-reasoning) [AA estimate]",
    "score": 18.29,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:bfe134e562d0cd53",
    "variant": "Artificial Analysis - MiMo-V2.5-Pro",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:9e023543b5154b09",
    "variant": "mimo-v2.5-pro",
    "score": 1477,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1471.6,
    "score_high": 1482.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c6879efca1b5dffc",
    "variant": "Mimo V2.5 Pro",
    "score": -7.23,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -8.14,
    "score_high": -6.32,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.04,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa241178a2088a2",
    "variant": "mini-swe-agent - mimo-v2-5-pro [vendor self-report]",
    "score": 19.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_day::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4f0191d02e894561",
    "variant": "MiMo-V2.5 [AA estimate]",
    "score": 25.1743,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5a02fb72c74be509",
    "variant": "Artificial Analysis - MiMo-V2.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_token_max_night::mimo-v2.5",
    "board": "arena_code",
    "configuration_id": "arena_code:101c12e441513d87",
    "variant": "mimo-v2.5",
    "score": 1438,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1432.0,
    "score_high": 1444.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:caaac19d5e8e542f",
    "variant": "GPT-5.6 Terra (max)",
    "score": 42.0829,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:660875fc06b206b1",
    "variant": "GPT-5.6 Terra (xhigh)",
    "score": 37.9513,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7d5413682aa8f8af",
    "variant": "GPT-5.6 Terra (high)",
    "score": 34.2377,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:32f3726769b48fd3",
    "variant": "GPT-5.6 Terra (medium)",
    "score": 30.0938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fcef5db6f44a9168",
    "variant": "GPT-5.6 Terra (low)",
    "score": 27.4962,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d3febc87f28b66bc",
    "variant": "GPT-5.6 Terra (non-reasoning)",
    "score": 20.7797,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:57a5da2cde308af0",
    "variant": "Codex - GPT-5.6 Terra (max)",
    "score": 21.52,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 18.27,
    "score_high": 24.77,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ce13a3cd68939ad",
    "variant": "Artificial Analysis - GPT-5.6 Terra (max)",
    "score": 35.3535,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:653b68c5fe321a32",
    "variant": "Artificial Analysis - GPT-5.6 Terra (xhigh)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8239d3088594c526",
    "variant": "Artificial Analysis - GPT-5.6 Terra (high)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b68acd500c6b4161",
    "variant": "Artificial Analysis - GPT-5.6 Terra (low)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9dda7394ba62eb25",
    "variant": "Artificial Analysis - GPT-5.6 Terra (medium)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2aa44c238da36b9a",
    "variant": "Artificial Analysis - GPT-5.6 Terra (non-reasoning)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "arena_code",
    "configuration_id": "arena_code:c67b556fb4592ef2",
    "variant": "gpt-5.6-terra-xhigh (codex-harness)",
    "score": 1519,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1512.4,
    "score_high": 1525.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:96e32efd63046574",
    "variant": "GPT 5.6 Terra (xHigh)",
    "score": 0.83,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -0.42000000000000004,
    "score_high": 2.08,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.43,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1e9b21c2004faec1",
    "variant": "mini-swe-agent - gpt-5-6-terra (max)",
    "score": 69.62305986696231,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 67.06612091651647,
    "score_high": 72.17999881740815,
    "mean_cost_usd_per_task": 4.945847263858093,
    "median_cost_usd_per_task": 4.114557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:277b6c07f6ca3318",
    "variant": "mini-swe-agent - gpt-5-6-terra (xhigh)",
    "score": 60.17699115044248,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 58.052693948515355,
    "score_high": 62.30128835236961,
    "mean_cost_usd_per_task": 2.127191725663717,
    "median_cost_usd_per_task": 1.8670102499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:31c29b4c94cf77ae",
    "variant": "mini-swe-agent - gpt-5-6-terra (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 49.432091479689106,
    "score_high": 58.09003241411621,
    "mean_cost_usd_per_task": 1.1343762765486725,
    "median_cost_usd_per_task": 1.031709,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:900c8577e3bc443d",
    "variant": "mini-swe-agent - gpt-5-6-terra (medium)",
    "score": 35.11111111111111,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 31.729146807704478,
    "score_high": 38.49307541451774,
    "mean_cost_usd_per_task": 0.5832493688888889,
    "median_cost_usd_per_task": 0.546099,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:329cf994aaf09cfd",
    "variant": "mini-swe-agent - gpt-5-6-terra (low)",
    "score": 24.053452115812917,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 23.276690748868134,
    "score_high": 24.830213482757703,
    "mean_cost_usd_per_task": 0.4277452605790646,
    "median_cost_usd_per_task": 0.3989895,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c4bfcb80a46cebef",
    "variant": "GPT-5.5 (xhigh)",
    "score": 38.3556,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6fd00cd9ccb51b99",
    "variant": "GPT-5.5 (high)",
    "score": 36.9794,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:22a192a88d4be69a",
    "variant": "GPT-5.5 (medium)",
    "score": 33.8044,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c3e9b37ac894d3d3",
    "variant": "GPT-5.5 (low) [AA estimate]",
    "score": 30.7095,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e75792c6ebb8bb80",
    "variant": "GPT-5.5 (non-reasoning) [AA estimate]",
    "score": 23.1674,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b426d7104b617616",
    "variant": "Artificial Analysis - GPT-5.5 (xhigh)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7bff670f3c107bb6",
    "variant": "Artificial Analysis - GPT-5.5 (high)",
    "score": 9.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:52b22206889b7f5e",
    "variant": "Artificial Analysis - GPT-5.5 (medium)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:8bba805c5e778260",
    "variant": "gpt-5.5-xhigh (codex-harness)",
    "score": 1512,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1506.1,
    "score_high": 1517.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:debea18029954afc",
    "variant": "gpt-5.5-high (codex-harness)",
    "score": 1487,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1481.1,
    "score_high": 1492.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:d0396ac7d382d35b",
    "variant": "gpt-5.5 (codex-harness)",
    "score": 1455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1449.1,
    "score_high": 1460.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:605f40536c85bbb4",
    "variant": "GPT 5.5 (xHigh)",
    "score": 4.12,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 3.0700000000000003,
    "score_high": 5.17,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.22,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f89b60d1061b77e1",
    "variant": "GPT 5.5",
    "score": 1.13,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.15999999999999992,
    "score_high": 2.0999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.61,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6d1742654e70dc7d",
    "variant": "mini-swe-agent - gpt-5-5 (xhigh)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 60.569751889179635,
    "score_high": 73.50104457099735,
    "mean_cost_usd_per_task": 7.226236674778761,
    "median_cost_usd_per_task": 6.110482499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa6331c80979ca8",
    "variant": "mini-swe-agent - gpt-5-5 (high)",
    "score": 64.38053097345133,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 61.26368832394585,
    "score_high": 67.49737362295679,
    "mean_cost_usd_per_task": 5.100437004424779,
    "median_cost_usd_per_task": 4.582879500000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f4c657e2ffa66931",
    "variant": "mini-swe-agent - gpt-5-5 (medium)",
    "score": 53.98230088495575,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.42921338966476,
    "score_high": 56.53538838024673,
    "mean_cost_usd_per_task": 2.749342734513274,
    "median_cost_usd_per_task": 2.436942,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_plus::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:94c61fbd52e4cefa",
    "variant": "mini-swe-agent - gpt-5-5 (low)",
    "score": 26.991150442477874,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 24.696647220470695,
    "score_high": 29.285653664485057,
    "mean_cost_usd_per_task": 1.2002025442477877,
    "median_cost_usd_per_task": 1.108106,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:caaac19d5e8e542f",
    "variant": "GPT-5.6 Terra (max)",
    "score": 42.0829,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:660875fc06b206b1",
    "variant": "GPT-5.6 Terra (xhigh)",
    "score": 37.9513,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7d5413682aa8f8af",
    "variant": "GPT-5.6 Terra (high)",
    "score": 34.2377,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:32f3726769b48fd3",
    "variant": "GPT-5.6 Terra (medium)",
    "score": 30.0938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fcef5db6f44a9168",
    "variant": "GPT-5.6 Terra (low)",
    "score": 27.4962,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d3febc87f28b66bc",
    "variant": "GPT-5.6 Terra (non-reasoning)",
    "score": 20.7797,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:57a5da2cde308af0",
    "variant": "Codex - GPT-5.6 Terra (max)",
    "score": 21.52,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 18.27,
    "score_high": 24.77,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ce13a3cd68939ad",
    "variant": "Artificial Analysis - GPT-5.6 Terra (max)",
    "score": 35.3535,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:653b68c5fe321a32",
    "variant": "Artificial Analysis - GPT-5.6 Terra (xhigh)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8239d3088594c526",
    "variant": "Artificial Analysis - GPT-5.6 Terra (high)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b68acd500c6b4161",
    "variant": "Artificial Analysis - GPT-5.6 Terra (low)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9dda7394ba62eb25",
    "variant": "Artificial Analysis - GPT-5.6 Terra (medium)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2aa44c238da36b9a",
    "variant": "Artificial Analysis - GPT-5.6 Terra (non-reasoning)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "arena_code",
    "configuration_id": "arena_code:c67b556fb4592ef2",
    "variant": "gpt-5.6-terra-xhigh (codex-harness)",
    "score": 1519,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1512.4,
    "score_high": 1525.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:96e32efd63046574",
    "variant": "GPT 5.6 Terra (xHigh)",
    "score": 0.83,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -0.42000000000000004,
    "score_high": 2.08,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.43,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1e9b21c2004faec1",
    "variant": "mini-swe-agent - gpt-5-6-terra (max)",
    "score": 69.62305986696231,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 67.06612091651647,
    "score_high": 72.17999881740815,
    "mean_cost_usd_per_task": 4.945847263858093,
    "median_cost_usd_per_task": 4.114557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:277b6c07f6ca3318",
    "variant": "mini-swe-agent - gpt-5-6-terra (xhigh)",
    "score": 60.17699115044248,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 58.052693948515355,
    "score_high": 62.30128835236961,
    "mean_cost_usd_per_task": 2.127191725663717,
    "median_cost_usd_per_task": 1.8670102499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:31c29b4c94cf77ae",
    "variant": "mini-swe-agent - gpt-5-6-terra (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 49.432091479689106,
    "score_high": 58.09003241411621,
    "mean_cost_usd_per_task": 1.1343762765486725,
    "median_cost_usd_per_task": 1.031709,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:900c8577e3bc443d",
    "variant": "mini-swe-agent - gpt-5-6-terra (medium)",
    "score": 35.11111111111111,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 31.729146807704478,
    "score_high": 38.49307541451774,
    "mean_cost_usd_per_task": 0.5832493688888889,
    "median_cost_usd_per_task": 0.546099,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:329cf994aaf09cfd",
    "variant": "mini-swe-agent - gpt-5-6-terra (low)",
    "score": 24.053452115812917,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 23.276690748868134,
    "score_high": 24.830213482757703,
    "mean_cost_usd_per_task": 0.4277452605790646,
    "median_cost_usd_per_task": 0.3989895,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c4bfcb80a46cebef",
    "variant": "GPT-5.5 (xhigh)",
    "score": 38.3556,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6fd00cd9ccb51b99",
    "variant": "GPT-5.5 (high)",
    "score": 36.9794,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:22a192a88d4be69a",
    "variant": "GPT-5.5 (medium)",
    "score": 33.8044,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c3e9b37ac894d3d3",
    "variant": "GPT-5.5 (low) [AA estimate]",
    "score": 30.7095,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e75792c6ebb8bb80",
    "variant": "GPT-5.5 (non-reasoning) [AA estimate]",
    "score": 23.1674,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b426d7104b617616",
    "variant": "Artificial Analysis - GPT-5.5 (xhigh)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7bff670f3c107bb6",
    "variant": "Artificial Analysis - GPT-5.5 (high)",
    "score": 9.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:52b22206889b7f5e",
    "variant": "Artificial Analysis - GPT-5.5 (medium)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:8bba805c5e778260",
    "variant": "gpt-5.5-xhigh (codex-harness)",
    "score": 1512,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1506.1,
    "score_high": 1517.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:debea18029954afc",
    "variant": "gpt-5.5-high (codex-harness)",
    "score": 1487,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1481.1,
    "score_high": 1492.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:d0396ac7d382d35b",
    "variant": "gpt-5.5 (codex-harness)",
    "score": 1455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1449.1,
    "score_high": 1460.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:605f40536c85bbb4",
    "variant": "GPT 5.5 (xHigh)",
    "score": 4.12,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 3.0700000000000003,
    "score_high": 5.17,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.22,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f89b60d1061b77e1",
    "variant": "GPT 5.5",
    "score": 1.13,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.15999999999999992,
    "score_high": 2.0999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.61,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6d1742654e70dc7d",
    "variant": "mini-swe-agent - gpt-5-5 (xhigh)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 60.569751889179635,
    "score_high": 73.50104457099735,
    "mean_cost_usd_per_task": 7.226236674778761,
    "median_cost_usd_per_task": 6.110482499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa6331c80979ca8",
    "variant": "mini-swe-agent - gpt-5-5 (high)",
    "score": 64.38053097345133,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 61.26368832394585,
    "score_high": 67.49737362295679,
    "mean_cost_usd_per_task": 5.100437004424779,
    "median_cost_usd_per_task": 4.582879500000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f4c657e2ffa66931",
    "variant": "mini-swe-agent - gpt-5-5 (medium)",
    "score": 53.98230088495575,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.42921338966476,
    "score_high": 56.53538838024673,
    "mean_cost_usd_per_task": 2.749342734513274,
    "median_cost_usd_per_task": 2.436942,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:94c61fbd52e4cefa",
    "variant": "mini-swe-agent - gpt-5-5 (low)",
    "score": 26.991150442477874,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 24.696647220470695,
    "score_high": 29.285653664485057,
    "mean_cost_usd_per_task": 1.2002025442477877,
    "median_cost_usd_per_task": 1.108106,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:caaac19d5e8e542f",
    "variant": "GPT-5.6 Terra (max)",
    "score": 42.0829,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:660875fc06b206b1",
    "variant": "GPT-5.6 Terra (xhigh)",
    "score": 37.9513,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7d5413682aa8f8af",
    "variant": "GPT-5.6 Terra (high)",
    "score": 34.2377,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:32f3726769b48fd3",
    "variant": "GPT-5.6 Terra (medium)",
    "score": 30.0938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fcef5db6f44a9168",
    "variant": "GPT-5.6 Terra (low)",
    "score": 27.4962,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d3febc87f28b66bc",
    "variant": "GPT-5.6 Terra (non-reasoning)",
    "score": 20.7797,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:57a5da2cde308af0",
    "variant": "Codex - GPT-5.6 Terra (max)",
    "score": 21.52,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 18.27,
    "score_high": 24.77,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ce13a3cd68939ad",
    "variant": "Artificial Analysis - GPT-5.6 Terra (max)",
    "score": 35.3535,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:653b68c5fe321a32",
    "variant": "Artificial Analysis - GPT-5.6 Terra (xhigh)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8239d3088594c526",
    "variant": "Artificial Analysis - GPT-5.6 Terra (high)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b68acd500c6b4161",
    "variant": "Artificial Analysis - GPT-5.6 Terra (low)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9dda7394ba62eb25",
    "variant": "Artificial Analysis - GPT-5.6 Terra (medium)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2aa44c238da36b9a",
    "variant": "Artificial Analysis - GPT-5.6 Terra (non-reasoning)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "arena_code",
    "configuration_id": "arena_code:c67b556fb4592ef2",
    "variant": "gpt-5.6-terra-xhigh (codex-harness)",
    "score": 1519,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1512.4,
    "score_high": 1525.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:96e32efd63046574",
    "variant": "GPT 5.6 Terra (xHigh)",
    "score": 0.83,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -0.42000000000000004,
    "score_high": 2.08,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.43,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1e9b21c2004faec1",
    "variant": "mini-swe-agent - gpt-5-6-terra (max)",
    "score": 69.62305986696231,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 67.06612091651647,
    "score_high": 72.17999881740815,
    "mean_cost_usd_per_task": 4.945847263858093,
    "median_cost_usd_per_task": 4.114557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:277b6c07f6ca3318",
    "variant": "mini-swe-agent - gpt-5-6-terra (xhigh)",
    "score": 60.17699115044248,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 58.052693948515355,
    "score_high": 62.30128835236961,
    "mean_cost_usd_per_task": 2.127191725663717,
    "median_cost_usd_per_task": 1.8670102499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:31c29b4c94cf77ae",
    "variant": "mini-swe-agent - gpt-5-6-terra (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 49.432091479689106,
    "score_high": 58.09003241411621,
    "mean_cost_usd_per_task": 1.1343762765486725,
    "median_cost_usd_per_task": 1.031709,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:900c8577e3bc443d",
    "variant": "mini-swe-agent - gpt-5-6-terra (medium)",
    "score": 35.11111111111111,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 31.729146807704478,
    "score_high": 38.49307541451774,
    "mean_cost_usd_per_task": 0.5832493688888889,
    "median_cost_usd_per_task": 0.546099,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:329cf994aaf09cfd",
    "variant": "mini-swe-agent - gpt-5-6-terra (low)",
    "score": 24.053452115812917,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 23.276690748868134,
    "score_high": 24.830213482757703,
    "mean_cost_usd_per_task": 0.4277452605790646,
    "median_cost_usd_per_task": 0.3989895,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c4bfcb80a46cebef",
    "variant": "GPT-5.5 (xhigh)",
    "score": 38.3556,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6fd00cd9ccb51b99",
    "variant": "GPT-5.5 (high)",
    "score": 36.9794,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:22a192a88d4be69a",
    "variant": "GPT-5.5 (medium)",
    "score": 33.8044,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c3e9b37ac894d3d3",
    "variant": "GPT-5.5 (low) [AA estimate]",
    "score": 30.7095,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e75792c6ebb8bb80",
    "variant": "GPT-5.5 (non-reasoning) [AA estimate]",
    "score": 23.1674,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b426d7104b617616",
    "variant": "Artificial Analysis - GPT-5.5 (xhigh)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7bff670f3c107bb6",
    "variant": "Artificial Analysis - GPT-5.5 (high)",
    "score": 9.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:52b22206889b7f5e",
    "variant": "Artificial Analysis - GPT-5.5 (medium)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:8bba805c5e778260",
    "variant": "gpt-5.5-xhigh (codex-harness)",
    "score": 1512,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1506.1,
    "score_high": 1517.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:debea18029954afc",
    "variant": "gpt-5.5-high (codex-harness)",
    "score": 1487,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1481.1,
    "score_high": 1492.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:d0396ac7d382d35b",
    "variant": "gpt-5.5 (codex-harness)",
    "score": 1455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1449.1,
    "score_high": 1460.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:605f40536c85bbb4",
    "variant": "GPT 5.5 (xHigh)",
    "score": 4.12,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 3.0700000000000003,
    "score_high": 5.17,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.22,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f89b60d1061b77e1",
    "variant": "GPT 5.5",
    "score": 1.13,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.15999999999999992,
    "score_high": 2.0999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.61,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6d1742654e70dc7d",
    "variant": "mini-swe-agent - gpt-5-5 (xhigh)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 60.569751889179635,
    "score_high": 73.50104457099735,
    "mean_cost_usd_per_task": 7.226236674778761,
    "median_cost_usd_per_task": 6.110482499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:8fa6331c80979ca8",
    "variant": "mini-swe-agent - gpt-5-5 (high)",
    "score": 64.38053097345133,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 61.26368832394585,
    "score_high": 67.49737362295679,
    "mean_cost_usd_per_task": 5.100437004424779,
    "median_cost_usd_per_task": 4.582879500000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f4c657e2ffa66931",
    "variant": "mini-swe-agent - gpt-5-5 (medium)",
    "score": 53.98230088495575,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.42921338966476,
    "score_high": 56.53538838024673,
    "mean_cost_usd_per_task": 2.749342734513274,
    "median_cost_usd_per_task": 2.436942,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_20x::gpt-5.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:94c61fbd52e4cefa",
    "variant": "mini-swe-agent - gpt-5-5 (low)",
    "score": 26.991150442477874,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 24.696647220470695,
    "score_high": 29.285653664485057,
    "mean_cost_usd_per_task": 1.2002025442477877,
    "median_cost_usd_per_task": 1.108106,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:00e5e17098f2a9cc",
    "variant": "Claude Sonnet 5 (max)",
    "score": 38.1639,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:26fc619ae9c44efb",
    "variant": "Claude Sonnet 5 (xhigh)",
    "score": 34.3842,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c089bab844997713",
    "variant": "Claude Sonnet 5 (high)",
    "score": 31.6623,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2b12f7c3563de350",
    "variant": "Claude Sonnet 5 (medium)",
    "score": 28.0531,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b99819b727eb71df",
    "variant": "Claude Sonnet 5 (low)",
    "score": 24.2638,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e35c69aedd168116",
    "variant": "Claude Sonnet 5 (non-reasoning) [AA estimate]",
    "score": 23.2,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5718a86e9278cdf2",
    "variant": "Claude Code - Sonnet 5 (max)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.36,
    "score_high": 15.48,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8a2bf906a5cca32e",
    "variant": "Artificial Analysis - Claude Sonnet 5 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:58f8a2ad361cbfac",
    "variant": "Artificial Analysis - Claude Sonnet 5 (xhigh)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4583c02c014dc3d1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (high)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a46e136780aeec1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (low)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:eecd341c62332c35",
    "variant": "Artificial Analysis - Claude Sonnet 5 (medium)",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "arena_code",
    "configuration_id": "arena_code:c91ce134bd5ec2e3",
    "variant": "claude-sonnet-5-high",
    "score": 1540,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1533.8,
    "score_high": 1546.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5729b5a20a335dfc",
    "variant": "Claude Sonnet 5 (High)",
    "score": 4.81,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 3.09,
    "score_high": 6.529999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:17f1ccadd79e3f73",
    "variant": "mini-swe-agent - claude-sonnet-5 (max)",
    "score": 53.84615384615385,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.60923737597946,
    "score_high": 58.08307031632823,
    "mean_cost_usd_per_task": 26.399858950791852,
    "median_cost_usd_per_task": 23.277376725000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6a089e055d07f388",
    "variant": "mini-swe-agent - claude-sonnet-5 (xhigh)",
    "score": 49.667405764966745,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 46.21285677328888,
    "score_high": 53.121954756644605,
    "mean_cost_usd_per_task": 11.890634540022173,
    "median_cost_usd_per_task": 9.965361750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e833a890e9fc6ef0",
    "variant": "mini-swe-agent - claude-sonnet-5 (high)",
    "score": 48.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 43.72377362536038,
    "score_high": 52.73640336579006,
    "mean_cost_usd_per_task": 7.425560161197339,
    "median_cost_usd_per_task": 5.833649100000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3cee9c2890b172bc",
    "variant": "mini-swe-agent - claude-sonnet-5 (medium)",
    "score": 39.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 36.65020157144805,
    "score_high": 42.90535398410751,
    "mean_cost_usd_per_task": 4.079036229,
    "median_cost_usd_per_task": 3.3573110999999995,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:4b4fac04da320c00",
    "variant": "mini-swe-agent - claude-sonnet-5 (low)",
    "score": 30.51224944320713,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 29.386231901764383,
    "score_high": 31.638266984649878,
    "mean_cost_usd_per_task": 2.1865550832962137,
    "median_cost_usd_per_task": 1.6764955500000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8ba60e513dcc3861",
    "variant": "Claude Opus 4.8 (max)",
    "score": 41.7899,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4b4e1e5e2f86b9f3",
    "variant": "Claude Code - Opus 4.8 (max)",
    "score": 23.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 20.080000000000002,
    "score_high": 27.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6569cb5d8342ed58",
    "variant": "Artificial Analysis - Claude Opus 4.8 (max)",
    "score": 21.7172,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:fae8bb30a0d7476b",
    "variant": "claude-opus-4-8-high",
    "score": 1556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1550.3,
    "score_high": 1561.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:00f9bf3b98edb73a",
    "variant": "claude-opus-4-8",
    "score": 1534,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1528.3,
    "score_high": 1539.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:263865305f7ecdb7",
    "variant": "Claude Opus 4.8 (High)",
    "score": 6.92,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 5.54,
    "score_high": 8.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.36,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:03fa5cc9c1b4bc14",
    "variant": "mini-swe-agent - claude-opus-4-8 (max)",
    "score": 58.97435897435898,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 57.20954362692973,
    "score_high": 60.73917432178823,
    "mean_cost_usd_per_task": 13.222583593240094,
    "median_cost_usd_per_task": 12.353505999999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9ba29daf22e9a1ae",
    "variant": "mini-swe-agent - claude-opus-4-8 (xhigh)",
    "score": 54.36241610738255,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.64898547928808,
    "score_high": 58.07584673547702,
    "mean_cost_usd_per_task": 8.006355704138702,
    "median_cost_usd_per_task": 7.049357750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2b59cc2e16364e15",
    "variant": "mini-swe-agent - claude-opus-4-8 (high)",
    "score": 51.76991150442478,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 47.20830235866894,
    "score_high": 56.33152065018062,
    "mean_cost_usd_per_task": 4.281940017699115,
    "median_cost_usd_per_task": 3.6635345,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7d16a6959bd957f6",
    "variant": "mini-swe-agent - claude-opus-4-8 (medium)",
    "score": 48.67256637168141,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 46.43336050994396,
    "score_high": 50.91177223341886,
    "mean_cost_usd_per_task": 3.4438571028761062,
    "median_cost_usd_per_task": 2.84043425,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:39deebcf76251bec",
    "variant": "mini-swe-agent - claude-opus-4-8 (low)",
    "score": 40.79822616407982,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.334641405510666,
    "score_high": 42.261810922648976,
    "mean_cost_usd_per_task": 2.293369216740577,
    "median_cost_usd_per_task": 1.8240152500000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:00e5e17098f2a9cc",
    "variant": "Claude Sonnet 5 (max)",
    "score": 38.1639,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:26fc619ae9c44efb",
    "variant": "Claude Sonnet 5 (xhigh)",
    "score": 34.3842,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c089bab844997713",
    "variant": "Claude Sonnet 5 (high)",
    "score": 31.6623,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2b12f7c3563de350",
    "variant": "Claude Sonnet 5 (medium)",
    "score": 28.0531,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b99819b727eb71df",
    "variant": "Claude Sonnet 5 (low)",
    "score": 24.2638,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e35c69aedd168116",
    "variant": "Claude Sonnet 5 (non-reasoning) [AA estimate]",
    "score": 23.2,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5718a86e9278cdf2",
    "variant": "Claude Code - Sonnet 5 (max)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.36,
    "score_high": 15.48,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8a2bf906a5cca32e",
    "variant": "Artificial Analysis - Claude Sonnet 5 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:58f8a2ad361cbfac",
    "variant": "Artificial Analysis - Claude Sonnet 5 (xhigh)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4583c02c014dc3d1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (high)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a46e136780aeec1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (low)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:eecd341c62332c35",
    "variant": "Artificial Analysis - Claude Sonnet 5 (medium)",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "arena_code",
    "configuration_id": "arena_code:c91ce134bd5ec2e3",
    "variant": "claude-sonnet-5-high",
    "score": 1540,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1533.8,
    "score_high": 1546.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5729b5a20a335dfc",
    "variant": "Claude Sonnet 5 (High)",
    "score": 4.81,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 3.09,
    "score_high": 6.529999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:17f1ccadd79e3f73",
    "variant": "mini-swe-agent - claude-sonnet-5 (max)",
    "score": 53.84615384615385,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.60923737597946,
    "score_high": 58.08307031632823,
    "mean_cost_usd_per_task": 26.399858950791852,
    "median_cost_usd_per_task": 23.277376725000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6a089e055d07f388",
    "variant": "mini-swe-agent - claude-sonnet-5 (xhigh)",
    "score": 49.667405764966745,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 46.21285677328888,
    "score_high": 53.121954756644605,
    "mean_cost_usd_per_task": 11.890634540022173,
    "median_cost_usd_per_task": 9.965361750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e833a890e9fc6ef0",
    "variant": "mini-swe-agent - claude-sonnet-5 (high)",
    "score": 48.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 43.72377362536038,
    "score_high": 52.73640336579006,
    "mean_cost_usd_per_task": 7.425560161197339,
    "median_cost_usd_per_task": 5.833649100000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3cee9c2890b172bc",
    "variant": "mini-swe-agent - claude-sonnet-5 (medium)",
    "score": 39.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 36.65020157144805,
    "score_high": 42.90535398410751,
    "mean_cost_usd_per_task": 4.079036229,
    "median_cost_usd_per_task": 3.3573110999999995,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:4b4fac04da320c00",
    "variant": "mini-swe-agent - claude-sonnet-5 (low)",
    "score": 30.51224944320713,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 29.386231901764383,
    "score_high": 31.638266984649878,
    "mean_cost_usd_per_task": 2.1865550832962137,
    "median_cost_usd_per_task": 1.6764955500000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8ba60e513dcc3861",
    "variant": "Claude Opus 4.8 (max)",
    "score": 41.7899,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4b4e1e5e2f86b9f3",
    "variant": "Claude Code - Opus 4.8 (max)",
    "score": 23.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 20.080000000000002,
    "score_high": 27.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6569cb5d8342ed58",
    "variant": "Artificial Analysis - Claude Opus 4.8 (max)",
    "score": 21.7172,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:fae8bb30a0d7476b",
    "variant": "claude-opus-4-8-high",
    "score": 1556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1550.3,
    "score_high": 1561.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:00f9bf3b98edb73a",
    "variant": "claude-opus-4-8",
    "score": 1534,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1528.3,
    "score_high": 1539.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:263865305f7ecdb7",
    "variant": "Claude Opus 4.8 (High)",
    "score": 6.92,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 5.54,
    "score_high": 8.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.36,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:03fa5cc9c1b4bc14",
    "variant": "mini-swe-agent - claude-opus-4-8 (max)",
    "score": 58.97435897435898,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 57.20954362692973,
    "score_high": 60.73917432178823,
    "mean_cost_usd_per_task": 13.222583593240094,
    "median_cost_usd_per_task": 12.353505999999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9ba29daf22e9a1ae",
    "variant": "mini-swe-agent - claude-opus-4-8 (xhigh)",
    "score": 54.36241610738255,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.64898547928808,
    "score_high": 58.07584673547702,
    "mean_cost_usd_per_task": 8.006355704138702,
    "median_cost_usd_per_task": 7.049357750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2b59cc2e16364e15",
    "variant": "mini-swe-agent - claude-opus-4-8 (high)",
    "score": 51.76991150442478,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 47.20830235866894,
    "score_high": 56.33152065018062,
    "mean_cost_usd_per_task": 4.281940017699115,
    "median_cost_usd_per_task": 3.6635345,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7d16a6959bd957f6",
    "variant": "mini-swe-agent - claude-opus-4-8 (medium)",
    "score": 48.67256637168141,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 46.43336050994396,
    "score_high": 50.91177223341886,
    "mean_cost_usd_per_task": 3.4438571028761062,
    "median_cost_usd_per_task": 2.84043425,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:39deebcf76251bec",
    "variant": "mini-swe-agent - claude-opus-4-8 (low)",
    "score": 40.79822616407982,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.334641405510666,
    "score_high": 42.261810922648976,
    "mean_cost_usd_per_task": 2.293369216740577,
    "median_cost_usd_per_task": 1.8240152500000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b5f20f46c907550",
    "variant": "Claude Fable 5 (with fallback)",
    "score": 49.6258,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:eb2874e55b9e0003",
    "variant": "Claude Code - Fable 5 (max)",
    "score": 44.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 40.699999999999996,
    "score_high": 48.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6fd65552e1fc1e0a",
    "variant": "Artificial Analysis - Claude Fable 5 (with fallback)",
    "score": 42.4242,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "arena_code",
    "configuration_id": "arena_code:72ebbd507122c58e",
    "variant": "claude-fable-5-high",
    "score": 1626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1619.6,
    "score_high": 1632.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3d3ae04ef0c99602",
    "variant": "Claude Fable 5 (High)",
    "score": 8.37,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.069999999999999,
    "score_high": 9.67,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.02,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:60791be82ce959e0",
    "variant": "mini-swe-agent - claude-fable-5 (xhigh)",
    "score": 69.91150442477876,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 66.66658684930744,
    "score_high": 73.15642200025007,
    "mean_cost_usd_per_task": 13.414521495535714,
    "median_cost_usd_per_task": 11.341082999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e5e5c5b317b1f68a",
    "variant": "mini-swe-agent - claude-fable-5 (max)",
    "score": 69.72477064220183,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.6912963913939,
    "score_high": 73.75824489300977,
    "mean_cost_usd_per_task": 21.634702092592594,
    "median_cost_usd_per_task": 19.23457225,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:42fd11a99a8570ba",
    "variant": "mini-swe-agent - claude-fable-5 (high)",
    "score": 68.6046511627907,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.48380844536031,
    "score_high": 69.7254938802211,
    "mean_cost_usd_per_task": 9.177638214788733,
    "median_cost_usd_per_task": 7.322686000000002,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a1709ab0b129e07e",
    "variant": "mini-swe-agent - claude-fable-5 (medium)",
    "score": 65.36697247706422,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 60.94504359782606,
    "score_high": 69.78890135630239,
    "mean_cost_usd_per_task": 6.088186528935186,
    "median_cost_usd_per_task": 4.62221125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:53874601b1d3b3da",
    "variant": "mini-swe-agent - claude-fable-5 (low)",
    "score": 59.58429561200924,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 56.79029016687951,
    "score_high": 62.37830105713898,
    "mean_cost_usd_per_task": 3.757873125874126,
    "median_cost_usd_per_task": 2.7559204999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:00e5e17098f2a9cc",
    "variant": "Claude Sonnet 5 (max)",
    "score": 38.1639,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:26fc619ae9c44efb",
    "variant": "Claude Sonnet 5 (xhigh)",
    "score": 34.3842,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c089bab844997713",
    "variant": "Claude Sonnet 5 (high)",
    "score": 31.6623,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2b12f7c3563de350",
    "variant": "Claude Sonnet 5 (medium)",
    "score": 28.0531,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b99819b727eb71df",
    "variant": "Claude Sonnet 5 (low)",
    "score": 24.2638,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e35c69aedd168116",
    "variant": "Claude Sonnet 5 (non-reasoning) [AA estimate]",
    "score": 23.2,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5718a86e9278cdf2",
    "variant": "Claude Code - Sonnet 5 (max)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.36,
    "score_high": 15.48,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8a2bf906a5cca32e",
    "variant": "Artificial Analysis - Claude Sonnet 5 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:58f8a2ad361cbfac",
    "variant": "Artificial Analysis - Claude Sonnet 5 (xhigh)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4583c02c014dc3d1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (high)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a46e136780aeec1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (low)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:eecd341c62332c35",
    "variant": "Artificial Analysis - Claude Sonnet 5 (medium)",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "arena_code",
    "configuration_id": "arena_code:c91ce134bd5ec2e3",
    "variant": "claude-sonnet-5-high",
    "score": 1540,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1533.8,
    "score_high": 1546.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5729b5a20a335dfc",
    "variant": "Claude Sonnet 5 (High)",
    "score": 4.81,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 3.09,
    "score_high": 6.529999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:17f1ccadd79e3f73",
    "variant": "mini-swe-agent - claude-sonnet-5 (max)",
    "score": 53.84615384615385,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.60923737597946,
    "score_high": 58.08307031632823,
    "mean_cost_usd_per_task": 26.399858950791852,
    "median_cost_usd_per_task": 23.277376725000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6a089e055d07f388",
    "variant": "mini-swe-agent - claude-sonnet-5 (xhigh)",
    "score": 49.667405764966745,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 46.21285677328888,
    "score_high": 53.121954756644605,
    "mean_cost_usd_per_task": 11.890634540022173,
    "median_cost_usd_per_task": 9.965361750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e833a890e9fc6ef0",
    "variant": "mini-swe-agent - claude-sonnet-5 (high)",
    "score": 48.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 43.72377362536038,
    "score_high": 52.73640336579006,
    "mean_cost_usd_per_task": 7.425560161197339,
    "median_cost_usd_per_task": 5.833649100000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3cee9c2890b172bc",
    "variant": "mini-swe-agent - claude-sonnet-5 (medium)",
    "score": 39.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 36.65020157144805,
    "score_high": 42.90535398410751,
    "mean_cost_usd_per_task": 4.079036229,
    "median_cost_usd_per_task": 3.3573110999999995,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:4b4fac04da320c00",
    "variant": "mini-swe-agent - claude-sonnet-5 (low)",
    "score": 30.51224944320713,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 29.386231901764383,
    "score_high": 31.638266984649878,
    "mean_cost_usd_per_task": 2.1865550832962137,
    "median_cost_usd_per_task": 1.6764955500000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b5f20f46c907550",
    "variant": "Claude Fable 5 (with fallback)",
    "score": 49.6258,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:eb2874e55b9e0003",
    "variant": "Claude Code - Fable 5 (max)",
    "score": 44.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 40.699999999999996,
    "score_high": 48.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6fd65552e1fc1e0a",
    "variant": "Artificial Analysis - Claude Fable 5 (with fallback)",
    "score": 42.4242,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "arena_code",
    "configuration_id": "arena_code:72ebbd507122c58e",
    "variant": "claude-fable-5-high",
    "score": 1626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1619.6,
    "score_high": 1632.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3d3ae04ef0c99602",
    "variant": "Claude Fable 5 (High)",
    "score": 8.37,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.069999999999999,
    "score_high": 9.67,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.02,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:60791be82ce959e0",
    "variant": "mini-swe-agent - claude-fable-5 (xhigh)",
    "score": 69.91150442477876,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 66.66658684930744,
    "score_high": 73.15642200025007,
    "mean_cost_usd_per_task": 13.414521495535714,
    "median_cost_usd_per_task": 11.341082999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e5e5c5b317b1f68a",
    "variant": "mini-swe-agent - claude-fable-5 (max)",
    "score": 69.72477064220183,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.6912963913939,
    "score_high": 73.75824489300977,
    "mean_cost_usd_per_task": 21.634702092592594,
    "median_cost_usd_per_task": 19.23457225,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:42fd11a99a8570ba",
    "variant": "mini-swe-agent - claude-fable-5 (high)",
    "score": 68.6046511627907,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.48380844536031,
    "score_high": 69.7254938802211,
    "mean_cost_usd_per_task": 9.177638214788733,
    "median_cost_usd_per_task": 7.322686000000002,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a1709ab0b129e07e",
    "variant": "mini-swe-agent - claude-fable-5 (medium)",
    "score": 65.36697247706422,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 60.94504359782606,
    "score_high": 69.78890135630239,
    "mean_cost_usd_per_task": 6.088186528935186,
    "median_cost_usd_per_task": 4.62221125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:53874601b1d3b3da",
    "variant": "mini-swe-agent - claude-fable-5 (low)",
    "score": 59.58429561200924,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 56.79029016687951,
    "score_high": 62.37830105713898,
    "mean_cost_usd_per_task": 3.757873125874126,
    "median_cost_usd_per_task": 2.7559204999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:71823637d973a0fc",
    "variant": "Claude Fable 5.1 (max with fallback)",
    "score": 53.3549,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3f66aafbb8812925",
    "variant": "Claude Fable 5.1 (xhigh with fallback)",
    "score": 53.2033,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:74265ef58fb6e45b",
    "variant": "Claude Fable 5.1 (high with fallback)",
    "score": 51.1516,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9a927f4404e32355",
    "variant": "Claude Fable 5.1 (medium with fallback)",
    "score": 48.9206,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ceeec877967a38a",
    "variant": "Claude Fable 5.1 (low with fallback)",
    "score": 46.8163,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:136537b36ce98c25",
    "variant": "Claude Code - Fable 5.1 (max)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.120000000000005,
    "score_high": 61.64,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cc67912665adccef",
    "variant": "Claude Code - Fable 5.1 (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.52,
    "score_high": 61.24,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:c1be8fa31509c696",
    "variant": "Claude Code - Fable 5.1 (high)",
    "score": 54.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.11,
    "score_high": 57.989999999999995,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5edd3a6853cd6339",
    "variant": "Claude Code - Fable 5.1 (medium)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 50.55,
    "score_high": 57.33,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4bcb6aba27442f07",
    "variant": "Claude Code - Fable 5.1 (low)",
    "score": 43.33,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.72,
    "score_high": 46.94,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:41e12ce515ec9121",
    "variant": "Artificial Analysis - Claude Fable 5.1 (xhigh with fallback)",
    "score": 55.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1512d68b0eb6bc1b",
    "variant": "Artificial Analysis - Claude Fable 5.1 (max with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e606b01ceda846f9",
    "variant": "Artificial Analysis - Claude Fable 5.1 (high with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:93ccfc6e6c1f4910",
    "variant": "Artificial Analysis - Claude Fable 5.1 (medium with fallback)",
    "score": 44.9495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5e01b08628a88aac",
    "variant": "Artificial Analysis - Claude Fable 5.1 (low with fallback)",
    "score": 40.404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:8e70472a84bf71d1",
    "variant": "claude-fable-5.1-max",
    "score": 1751,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1741.3,
    "score_high": 1760.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:d1cdd70383ae2039",
    "variant": "Claude Fable 5.1 (Max)",
    "score": 14.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 12.63,
    "score_high": 16.47,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 4.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:f882189259104e87",
    "variant": "Claude Code - Fable 5.1 (max) (with fallback)",
    "score": 62.2225,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 12.3881,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1041b2cdd9886064",
    "variant": "Devin Fusion CLI - Claude Fable 5.1 XHigh + SWE-2 Medium",
    "score": 61.6826,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.8971,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-fable-5.1",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:0ed675e0b61ae3ac",
    "variant": "Claude Fable 5.1",
    "score": 80.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.660199,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_pro::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_20x::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "claude_max_5x::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b1da82a91856d8d",
    "variant": "GPT-6 Astra (max)",
    "score": 52.6737,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7070b585da6e3a29",
    "variant": "GPT-6 Astra (xhigh)",
    "score": 52.3863,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7c09034755a992fc",
    "variant": "GPT-6 Astra (high)",
    "score": 50.9191,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3cf95b4f1be42e0f",
    "variant": "GPT-6 Astra (medium)",
    "score": 49.5704,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6858c62f40a2b8a3",
    "variant": "GPT-6 Astra (low)",
    "score": 45.7819,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:e5bdec03718dfb8f",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 58.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 55.39,
    "score_high": 60.97,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:d1970c4faffe81bc",
    "variant": "Codex - GPT-6 Astra (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 55.160000000000004,
    "score_high": 60.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:425d97cf71b364f9",
    "variant": "Codex - GPT-6 Astra (high)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 54.910000000000004,
    "score_high": 60.85,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1ebcc077b6f11845",
    "variant": "Codex - GPT-6 Astra (medium)",
    "score": 54.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.58,
    "score_high": 56.900000000000006,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:6c09cda642c293be",
    "variant": "Codex - GPT-6 Astra (low)",
    "score": 50.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 47.86,
    "score_high": 53.36,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:700453154be041cb",
    "variant": "Artificial Analysis - GPT-6 Astra (xhigh)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e44812025afd889c",
    "variant": "Artificial Analysis - GPT-6 Astra (max)",
    "score": 59.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:12ee7971061ca0e0",
    "variant": "Artificial Analysis - GPT-6 Astra (high)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0634c4abcbad70cc",
    "variant": "Artificial Analysis - GPT-6 Astra (medium)",
    "score": 49.4949,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4785a3610e775817",
    "variant": "Artificial Analysis - GPT-6 Astra (low)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "arena_code",
    "configuration_id": "arena_code:2fa5b191581aaf87",
    "variant": "gpt-6-astra-max",
    "score": 1789,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1778.6,
    "score_high": 1799.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:704fea58650c673b",
    "variant": "GPT 6 Astra (Max)",
    "score": 12.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.9,
    "score_high": 14.459999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6ee94ff7d755eeee",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 61.645,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.4671,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:c64a6ebb32778718",
    "variant": "Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium",
    "score": 58.8884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.5365,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:eab6a68a5b32527b",
    "variant": "GPT-6 Astra",
    "score": 82.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.612939,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aa4ad931eff45be4",
    "variant": "mini-swe-agent - gpt-6-astra (xhigh)",
    "score": 74.11504424778761,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 71.24964807371246,
    "score_high": 76.98044042186275,
    "mean_cost_usd_per_task": 6.52377356460177,
    "median_cost_usd_per_task": 5.6717151,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e8101649c60ecba8",
    "variant": "mini-swe-agent - gpt-6-astra (high)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 69.80659243770221,
    "score_high": 76.65358455344823,
    "mean_cost_usd_per_task": 5.723721956194691,
    "median_cost_usd_per_task": 4.9622669,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b30a594ec5f66ce7",
    "variant": "mini-swe-agent - gpt-6-astra (max)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 72.39976873936956,
    "score_high": 74.06040825178087,
    "mean_cost_usd_per_task": 12.369032401327434,
    "median_cost_usd_per_task": 11.036936,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a5c5cd4b12673627",
    "variant": "mini-swe-agent - gpt-6-astra (medium)",
    "score": 72.78761061946902,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 70.19796153763716,
    "score_high": 75.37725970130089,
    "mean_cost_usd_per_task": 4.379527705752213,
    "median_cost_usd_per_task": 3.7133415999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "chatgpt_pro_5x::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2d2b1fb9f6df06a3",
    "variant": "mini-swe-agent - gpt-6-astra (low)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 65.73453717840262,
    "score_high": 68.33625928177437,
    "mean_cost_usd_per_task": 2.188762706637168,
    "median_cost_usd_per_task": 1.7209886,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:829ff4209a0293bc",
    "variant": "Grok 4.5 (high)",
    "score": 38.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:98d088ff379b956d",
    "variant": "Grok Build - Grok 4.5 (high)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 9.8,
    "score_high": 15.04,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:68bfb23c4047a7a3",
    "variant": "Artificial Analysis - Grok 4.5 (high)",
    "score": 10.6061,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "arena_code",
    "configuration_id": "arena_code:dc0921a30ecddd2c",
    "variant": "grok-4.5",
    "score": 1552,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1545.4,
    "score_high": 1558.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:069dfce97d9ef41d",
    "variant": "Grok 4.5",
    "score": 1.11,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.1200000000000001,
    "score_high": 2.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "cursor_ultra::grok-4.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:70b6e868fcb9cd80",
    "variant": "mini-swe-agent - grok-4-5 (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.48025737402474,
    "score_high": 56.04186651978057,
    "mean_cost_usd_per_task": 2.4157481725663716,
    "median_cost_usd_per_task": 2.02311,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:829ff4209a0293bc",
    "variant": "Grok 4.5 (high)",
    "score": 38.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:98d088ff379b956d",
    "variant": "Grok Build - Grok 4.5 (high)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 9.8,
    "score_high": 15.04,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:68bfb23c4047a7a3",
    "variant": "Artificial Analysis - Grok 4.5 (high)",
    "score": 10.6061,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "arena_code",
    "configuration_id": "arena_code:dc0921a30ecddd2c",
    "variant": "grok-4.5",
    "score": 1552,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1545.4,
    "score_high": 1558.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:069dfce97d9ef41d",
    "variant": "Grok 4.5",
    "score": 1.11,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.1200000000000001,
    "score_high": 2.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok_heavy::grok-4.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:70b6e868fcb9cd80",
    "variant": "mini-swe-agent - grok-4-5 (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.48025737402474,
    "score_high": 56.04186651978057,
    "mean_cost_usd_per_task": 2.4157481725663716,
    "median_cost_usd_per_task": 2.02311,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:829ff4209a0293bc",
    "variant": "Grok 4.5 (high)",
    "score": 38.8121,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:98d088ff379b956d",
    "variant": "Grok Build - Grok 4.5 (high)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 9.8,
    "score_high": 15.04,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:68bfb23c4047a7a3",
    "variant": "Artificial Analysis - Grok 4.5 (high)",
    "score": 10.6061,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "arena_code",
    "configuration_id": "arena_code:dc0921a30ecddd2c",
    "variant": "grok-4.5",
    "score": 1552,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1545.4,
    "score_high": 1558.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:069dfce97d9ef41d",
    "variant": "Grok 4.5",
    "score": 1.11,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 0.1200000000000001,
    "score_high": 2.1,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "supergrok::grok-4.5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:70b6e868fcb9cd80",
    "variant": "mini-swe-agent - grok-4-5 (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.48025737402474,
    "score_high": 56.04186651978057,
    "mean_cost_usd_per_task": 2.4157481725663716,
    "median_cost_usd_per_task": 2.02311,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:71823637d973a0fc",
    "variant": "Claude Fable 5.1 (max with fallback)",
    "score": 53.3549,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3f66aafbb8812925",
    "variant": "Claude Fable 5.1 (xhigh with fallback)",
    "score": 53.2033,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:74265ef58fb6e45b",
    "variant": "Claude Fable 5.1 (high with fallback)",
    "score": 51.1516,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9a927f4404e32355",
    "variant": "Claude Fable 5.1 (medium with fallback)",
    "score": 48.9206,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ceeec877967a38a",
    "variant": "Claude Fable 5.1 (low with fallback)",
    "score": 46.8163,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:136537b36ce98c25",
    "variant": "Claude Code - Fable 5.1 (max)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.120000000000005,
    "score_high": 61.64,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cc67912665adccef",
    "variant": "Claude Code - Fable 5.1 (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.52,
    "score_high": 61.24,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:c1be8fa31509c696",
    "variant": "Claude Code - Fable 5.1 (high)",
    "score": 54.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.11,
    "score_high": 57.989999999999995,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5edd3a6853cd6339",
    "variant": "Claude Code - Fable 5.1 (medium)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 50.55,
    "score_high": 57.33,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4bcb6aba27442f07",
    "variant": "Claude Code - Fable 5.1 (low)",
    "score": 43.33,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.72,
    "score_high": 46.94,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:41e12ce515ec9121",
    "variant": "Artificial Analysis - Claude Fable 5.1 (xhigh with fallback)",
    "score": 55.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1512d68b0eb6bc1b",
    "variant": "Artificial Analysis - Claude Fable 5.1 (max with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e606b01ceda846f9",
    "variant": "Artificial Analysis - Claude Fable 5.1 (high with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:93ccfc6e6c1f4910",
    "variant": "Artificial Analysis - Claude Fable 5.1 (medium with fallback)",
    "score": 44.9495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5e01b08628a88aac",
    "variant": "Artificial Analysis - Claude Fable 5.1 (low with fallback)",
    "score": 40.404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:8e70472a84bf71d1",
    "variant": "claude-fable-5.1-max",
    "score": 1751,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1741.3,
    "score_high": 1760.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:d1cdd70383ae2039",
    "variant": "Claude Fable 5.1 (Max)",
    "score": 14.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 12.63,
    "score_high": 16.47,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 4.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:f882189259104e87",
    "variant": "Claude Code - Fable 5.1 (max) (with fallback)",
    "score": 62.2225,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 12.3881,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1041b2cdd9886064",
    "variant": "Devin Fusion CLI - Claude Fable 5.1 XHigh + SWE-2 Medium",
    "score": 61.6826,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.8971,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5.1",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:0ed675e0b61ae3ac",
    "variant": "Claude Fable 5.1",
    "score": 80.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.660199,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b5f20f46c907550",
    "variant": "Claude Fable 5 (with fallback)",
    "score": 49.6258,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:eb2874e55b9e0003",
    "variant": "Claude Code - Fable 5 (max)",
    "score": 44.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 40.699999999999996,
    "score_high": 48.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6fd65552e1fc1e0a",
    "variant": "Artificial Analysis - Claude Fable 5 (with fallback)",
    "score": 42.4242,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "arena_code",
    "configuration_id": "arena_code:72ebbd507122c58e",
    "variant": "claude-fable-5-high",
    "score": 1626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1619.6,
    "score_high": 1632.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3d3ae04ef0c99602",
    "variant": "Claude Fable 5 (High)",
    "score": 8.37,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.069999999999999,
    "score_high": 9.67,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.02,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:60791be82ce959e0",
    "variant": "mini-swe-agent - claude-fable-5 (xhigh)",
    "score": 69.91150442477876,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 66.66658684930744,
    "score_high": 73.15642200025007,
    "mean_cost_usd_per_task": 13.414521495535714,
    "median_cost_usd_per_task": 11.341082999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e5e5c5b317b1f68a",
    "variant": "mini-swe-agent - claude-fable-5 (max)",
    "score": 69.72477064220183,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.6912963913939,
    "score_high": 73.75824489300977,
    "mean_cost_usd_per_task": 21.634702092592594,
    "median_cost_usd_per_task": 19.23457225,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:42fd11a99a8570ba",
    "variant": "mini-swe-agent - claude-fable-5 (high)",
    "score": 68.6046511627907,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.48380844536031,
    "score_high": 69.7254938802211,
    "mean_cost_usd_per_task": 9.177638214788733,
    "median_cost_usd_per_task": 7.322686000000002,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a1709ab0b129e07e",
    "variant": "mini-swe-agent - claude-fable-5 (medium)",
    "score": 65.36697247706422,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 60.94504359782606,
    "score_high": 69.78890135630239,
    "mean_cost_usd_per_task": 6.088186528935186,
    "median_cost_usd_per_task": 4.62221125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:53874601b1d3b3da",
    "variant": "mini-swe-agent - claude-fable-5 (low)",
    "score": 59.58429561200924,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 56.79029016687951,
    "score_high": 62.37830105713898,
    "mean_cost_usd_per_task": 3.757873125874126,
    "median_cost_usd_per_task": 2.7559204999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:68425237e9876779",
    "variant": "Claude Opus 5 (max)",
    "score": 50.7771,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a154cb4e9c99189",
    "variant": "Claude Opus 5 (xhigh)",
    "score": 49.6774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:295f5f7bdfa8d248",
    "variant": "Claude Opus 5 (high)",
    "score": 48.1219,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bacfec5f5f91d13c",
    "variant": "Claude Opus 5 (medium)",
    "score": 44.8253,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e42133cf9100a842",
    "variant": "Claude Opus 5 (low)",
    "score": 39.3543,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7d59ed14e6a26f29",
    "variant": "Claude Code - Opus 5 (xhigh)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.769999999999996,
    "score_high": 57.11,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cec3b7db483cca26",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 51.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 48.43,
    "score_high": 55.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:82e30cded058a067",
    "variant": "Claude Code - Opus 5 (high)",
    "score": 50.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 46.57,
    "score_high": 54.029999999999994,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:314e4521dd78b2f2",
    "variant": "Claude Code - Opus 5 (medium)",
    "score": 44.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 41.02,
    "score_high": 48.68,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:3ef9fcfb65e0cb76",
    "variant": "Claude Code - Opus 5 (low)",
    "score": 34.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 30.91,
    "score_high": 38.79,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ed48e92962897a4",
    "variant": "Artificial Analysis - Claude Opus 5 (max)",
    "score": 48.9899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0838ca37e5fa42da",
    "variant": "Artificial Analysis - Claude Opus 5 (xhigh)",
    "score": 46.4646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8e10956f03aaa14d",
    "variant": "Artificial Analysis - Claude Opus 5 (high)",
    "score": 45.9596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:314fe657e048e298",
    "variant": "Artificial Analysis - Claude Opus 5 (medium)",
    "score": 34.3434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a61fb5355f7888c8",
    "variant": "Artificial Analysis - Claude Opus 5 (low)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:3aa3e36faa602970",
    "variant": "claude-opus-5-max",
    "score": 1694,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1687.5,
    "score_high": 1700.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:6b8714542169429d",
    "variant": "claude-opus-5-high",
    "score": 1660,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1654.3,
    "score_high": 1665.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:63ab115851e0de58",
    "variant": "Claude Opus 5 (High)",
    "score": 8.76,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.26,
    "score_high": 10.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.5,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:7b426212aba5971e",
    "variant": "Claude Opus 5 (Max)",
    "score": 8.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 6.98,
    "score_high": 10.120000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 3.59,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:e0b71dfaa4f1714e",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 59.7264,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 10.7892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f029cafdaf0a4ee3",
    "variant": "mini-swe-agent - claude-opus-5 (max)",
    "score": 73.64864864864865,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.77633822227692,
    "score_high": 77.52095907502039,
    "mean_cost_usd_per_task": 11.837583271396396,
    "median_cost_usd_per_task": 10.4281505,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:853cb17f0e600556",
    "variant": "mini-swe-agent - claude-opus-5 (xhigh)",
    "score": 73.15436241610739,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 70.09338059446893,
    "score_high": 76.21534423774585,
    "mean_cost_usd_per_task": 9.07220232326622,
    "median_cost_usd_per_task": 7.928816750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e252d58fa6da2ebe",
    "variant": "mini-swe-agent - claude-opus-5 (high)",
    "score": 72.82850779510022,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 70.88307563794007,
    "score_high": 74.77393995226038,
    "mean_cost_usd_per_task": 6.076084489977728,
    "median_cost_usd_per_task": 4.96882375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:df5db3bddc1856ee",
    "variant": "mini-swe-agent - claude-opus-5 (medium)",
    "score": 68.90380313199105,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 67.73124446609795,
    "score_high": 70.07636179788415,
    "mean_cost_usd_per_task": 3.28978764541387,
    "median_cost_usd_per_task": 2.4819885000000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3353f4eaaecc0e42",
    "variant": "mini-swe-agent - claude-opus-5 (low)",
    "score": 58.12917594654788,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 55.79848799986361,
    "score_high": 60.45986389323216,
    "mean_cost_usd_per_task": 1.6626223919821828,
    "median_cost_usd_per_task": 1.2162672499999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8ba60e513dcc3861",
    "variant": "Claude Opus 4.8 (max)",
    "score": 41.7899,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4b4e1e5e2f86b9f3",
    "variant": "Claude Code - Opus 4.8 (max)",
    "score": 23.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 20.080000000000002,
    "score_high": 27.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6569cb5d8342ed58",
    "variant": "Artificial Analysis - Claude Opus 4.8 (max)",
    "score": 21.7172,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:fae8bb30a0d7476b",
    "variant": "claude-opus-4-8-high",
    "score": 1556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1550.3,
    "score_high": 1561.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "arena_code",
    "configuration_id": "arena_code:00f9bf3b98edb73a",
    "variant": "claude-opus-4-8",
    "score": 1534,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1528.3,
    "score_high": 1539.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:263865305f7ecdb7",
    "variant": "Claude Opus 4.8 (High)",
    "score": 6.92,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 5.54,
    "score_high": 8.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.36,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:03fa5cc9c1b4bc14",
    "variant": "mini-swe-agent - claude-opus-4-8 (max)",
    "score": 58.97435897435898,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 57.20954362692973,
    "score_high": 60.73917432178823,
    "mean_cost_usd_per_task": 13.222583593240094,
    "median_cost_usd_per_task": 12.353505999999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9ba29daf22e9a1ae",
    "variant": "mini-swe-agent - claude-opus-4-8 (xhigh)",
    "score": 54.36241610738255,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.64898547928808,
    "score_high": 58.07584673547702,
    "mean_cost_usd_per_task": 8.006355704138702,
    "median_cost_usd_per_task": 7.049357750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2b59cc2e16364e15",
    "variant": "mini-swe-agent - claude-opus-4-8 (high)",
    "score": 51.76991150442478,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 47.20830235866894,
    "score_high": 56.33152065018062,
    "mean_cost_usd_per_task": 4.281940017699115,
    "median_cost_usd_per_task": 3.6635345,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7d16a6959bd957f6",
    "variant": "mini-swe-agent - claude-opus-4-8 (medium)",
    "score": 48.67256637168141,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 46.43336050994396,
    "score_high": 50.91177223341886,
    "mean_cost_usd_per_task": 3.4438571028761062,
    "median_cost_usd_per_task": 2.84043425,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-opus-4.8",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:39deebcf76251bec",
    "variant": "mini-swe-agent - claude-opus-4-8 (low)",
    "score": 40.79822616407982,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.334641405510666,
    "score_high": 42.261810922648976,
    "mean_cost_usd_per_task": 2.293369216740577,
    "median_cost_usd_per_task": 1.8240152500000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b1da82a91856d8d",
    "variant": "GPT-6 Astra (max)",
    "score": 52.6737,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7070b585da6e3a29",
    "variant": "GPT-6 Astra (xhigh)",
    "score": 52.3863,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7c09034755a992fc",
    "variant": "GPT-6 Astra (high)",
    "score": 50.9191,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3cf95b4f1be42e0f",
    "variant": "GPT-6 Astra (medium)",
    "score": 49.5704,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6858c62f40a2b8a3",
    "variant": "GPT-6 Astra (low)",
    "score": 45.7819,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:e5bdec03718dfb8f",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 58.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 55.39,
    "score_high": 60.97,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:d1970c4faffe81bc",
    "variant": "Codex - GPT-6 Astra (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 55.160000000000004,
    "score_high": 60.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:425d97cf71b364f9",
    "variant": "Codex - GPT-6 Astra (high)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 54.910000000000004,
    "score_high": 60.85,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1ebcc077b6f11845",
    "variant": "Codex - GPT-6 Astra (medium)",
    "score": 54.24,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 51.58,
    "score_high": 56.900000000000006,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:6c09cda642c293be",
    "variant": "Codex - GPT-6 Astra (low)",
    "score": 50.61,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 47.86,
    "score_high": 53.36,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:700453154be041cb",
    "variant": "Artificial Analysis - GPT-6 Astra (xhigh)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e44812025afd889c",
    "variant": "Artificial Analysis - GPT-6 Astra (max)",
    "score": 59.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:12ee7971061ca0e0",
    "variant": "Artificial Analysis - GPT-6 Astra (high)",
    "score": 54.0404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0634c4abcbad70cc",
    "variant": "Artificial Analysis - GPT-6 Astra (medium)",
    "score": 49.4949,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4785a3610e775817",
    "variant": "Artificial Analysis - GPT-6 Astra (low)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "arena_code",
    "configuration_id": "arena_code:2fa5b191581aaf87",
    "variant": "gpt-6-astra-max",
    "score": 1789,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1778.6,
    "score_high": 1799.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:704fea58650c673b",
    "variant": "GPT 6 Astra (Max)",
    "score": 12.18,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.9,
    "score_high": 14.459999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:6ee94ff7d755eeee",
    "variant": "Codex - GPT-6 Astra (max)",
    "score": 61.645,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.4671,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:c64a6ebb32778718",
    "variant": "Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium",
    "score": 58.8884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.5365,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:eab6a68a5b32527b",
    "variant": "GPT-6 Astra",
    "score": 82.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.612939,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aa4ad931eff45be4",
    "variant": "mini-swe-agent - gpt-6-astra (xhigh)",
    "score": 74.11504424778761,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 71.24964807371246,
    "score_high": 76.98044042186275,
    "mean_cost_usd_per_task": 6.52377356460177,
    "median_cost_usd_per_task": 5.6717151,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e8101649c60ecba8",
    "variant": "mini-swe-agent - gpt-6-astra (high)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 69.80659243770221,
    "score_high": 76.65358455344823,
    "mean_cost_usd_per_task": 5.723721956194691,
    "median_cost_usd_per_task": 4.9622669,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b30a594ec5f66ce7",
    "variant": "mini-swe-agent - gpt-6-astra (max)",
    "score": 73.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 72.39976873936956,
    "score_high": 74.06040825178087,
    "mean_cost_usd_per_task": 12.369032401327434,
    "median_cost_usd_per_task": 11.036936,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a5c5cd4b12673627",
    "variant": "mini-swe-agent - gpt-6-astra (medium)",
    "score": 72.78761061946902,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 70.19796153763716,
    "score_high": 75.37725970130089,
    "mean_cost_usd_per_task": 4.379527705752213,
    "median_cost_usd_per_task": 3.7133415999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-astra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2d2b1fb9f6df06a3",
    "variant": "mini-swe-agent - gpt-6-astra (low)",
    "score": 67.03539823008849,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 65.73453717840262,
    "score_high": 68.33625928177437,
    "mean_cost_usd_per_task": 2.188762706637168,
    "median_cost_usd_per_task": 1.7209886,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ca545106241767d7",
    "variant": "GPT-6 Sol (max)",
    "score": 47.5276,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ec3291a5ccf1d360",
    "variant": "GPT-6 Sol (xhigh)",
    "score": 44.101,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b88d90b9ef2bcc13",
    "variant": "GPT-6 Sol (high)",
    "score": 42.8216,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5dea08c56cadf0a5",
    "variant": "GPT-6 Sol (medium)",
    "score": 39.7821,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db3deb60f0a6f0ac",
    "variant": "GPT-6 Sol (low)",
    "score": 33.9009,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:49ed8f07e3584753",
    "variant": "GPT-6 Sol (non-reasoning)",
    "score": 28.0922,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c54c846fa56e7fb9",
    "variant": "Artificial Analysis - GPT-6 Sol (max)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ba48609dee4ff716",
    "variant": "Artificial Analysis - GPT-6 Sol (xhigh)",
    "score": 30.303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2ac75acfdd5556ef",
    "variant": "Artificial Analysis - GPT-6 Sol (high)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b54a5c8b54994f4",
    "variant": "Artificial Analysis - GPT-6 Sol (medium)",
    "score": 18.6869,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ba96dfd07fb6e2bc",
    "variant": "Artificial Analysis - GPT-6 Sol (non-reasoning)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:af9e50a31779df75",
    "variant": "Artificial Analysis - GPT-6 Sol (low)",
    "score": 9.0909,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:99658ae7db6b17a4",
    "variant": "gpt-6-sol-max",
    "score": 1689,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1677.2,
    "score_high": 1700.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c3f5ba38fbb30407",
    "variant": "GPT 6 Sol (Max)",
    "score": 10.65,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 8.08,
    "score_high": 13.22,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.91,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:a5a1b714fe3ad343",
    "variant": "Codex - GPT-6 Sol (max)",
    "score": 56.6626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.9897,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:63b060c2709bd850",
    "variant": "GPT-6 Sol",
    "score": 89.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.296641,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e41e4b6709da24d4",
    "variant": "GPT-6 Luna (max)",
    "score": 37.256,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:711bafc42ade2516",
    "variant": "GPT-6 Luna (xhigh)",
    "score": 33.8846,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:927f29d66e09bcc0",
    "variant": "GPT-6 Luna (high)",
    "score": 32.1482,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:51051c5b6fc81a75",
    "variant": "GPT-6 Luna (medium)",
    "score": 29.462,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9e4a1080bc5cdeda",
    "variant": "GPT-6 Luna (low)",
    "score": 20.9225,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:be701ec71aacde7a",
    "variant": "GPT-6 Luna (non-reasoning)",
    "score": 18.2617,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4d4153eb38f2e84f",
    "variant": "Artificial Analysis - GPT-6 Luna (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3956f4765e345bfa",
    "variant": "Artificial Analysis - GPT-6 Luna (xhigh)",
    "score": 8.0808,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:964384bb8d3b9a13",
    "variant": "Artificial Analysis - GPT-6 Luna (high)",
    "score": 4.5455,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:62b32b0accfdc3e1",
    "variant": "Artificial Analysis - GPT-6 Luna (medium)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c911fafd76fe1373",
    "variant": "Artificial Analysis - GPT-6 Luna (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1f723b35d187e5ec",
    "variant": "Artificial Analysis - GPT-6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:27376aa104f48f0e",
    "variant": "gpt-6-luna-max",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1573.0,
    "score_high": 1591.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:04bd9ba65c143398",
    "variant": "GPT 6 Luna (Max)",
    "score": 1.68,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 0.27,
    "score_high": 3.09,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.06,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:01e2ffcaa1665576",
    "variant": "Codex - GPT-6 Luna (max)",
    "score": 41.0744,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.1759,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-6-luna",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:df380d7af56a8dd0",
    "variant": "GPT-6 Luna",
    "score": 83.1,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.015871,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:caaac19d5e8e542f",
    "variant": "GPT-5.6 Terra (max)",
    "score": 42.0829,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:660875fc06b206b1",
    "variant": "GPT-5.6 Terra (xhigh)",
    "score": 37.9513,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7d5413682aa8f8af",
    "variant": "GPT-5.6 Terra (high)",
    "score": 34.2377,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:32f3726769b48fd3",
    "variant": "GPT-5.6 Terra (medium)",
    "score": 30.0938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fcef5db6f44a9168",
    "variant": "GPT-5.6 Terra (low)",
    "score": 27.4962,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d3febc87f28b66bc",
    "variant": "GPT-5.6 Terra (non-reasoning)",
    "score": 20.7797,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:57a5da2cde308af0",
    "variant": "Codex - GPT-5.6 Terra (max)",
    "score": 21.52,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 18.27,
    "score_high": 24.77,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ce13a3cd68939ad",
    "variant": "Artificial Analysis - GPT-5.6 Terra (max)",
    "score": 35.3535,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:653b68c5fe321a32",
    "variant": "Artificial Analysis - GPT-5.6 Terra (xhigh)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8239d3088594c526",
    "variant": "Artificial Analysis - GPT-5.6 Terra (high)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b68acd500c6b4161",
    "variant": "Artificial Analysis - GPT-5.6 Terra (low)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9dda7394ba62eb25",
    "variant": "Artificial Analysis - GPT-5.6 Terra (medium)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2aa44c238da36b9a",
    "variant": "Artificial Analysis - GPT-5.6 Terra (non-reasoning)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "arena_code",
    "configuration_id": "arena_code:c67b556fb4592ef2",
    "variant": "gpt-5.6-terra-xhigh (codex-harness)",
    "score": 1519,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1512.4,
    "score_high": 1525.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:96e32efd63046574",
    "variant": "GPT 5.6 Terra (xHigh)",
    "score": 0.83,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -0.42000000000000004,
    "score_high": 2.08,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.43,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1e9b21c2004faec1",
    "variant": "mini-swe-agent - gpt-5-6-terra (max)",
    "score": 69.62305986696231,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 67.06612091651647,
    "score_high": 72.17999881740815,
    "mean_cost_usd_per_task": 4.945847263858093,
    "median_cost_usd_per_task": 4.114557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:277b6c07f6ca3318",
    "variant": "mini-swe-agent - gpt-5-6-terra (xhigh)",
    "score": 60.17699115044248,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 58.052693948515355,
    "score_high": 62.30128835236961,
    "mean_cost_usd_per_task": 2.127191725663717,
    "median_cost_usd_per_task": 1.8670102499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:31c29b4c94cf77ae",
    "variant": "mini-swe-agent - gpt-5-6-terra (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 49.432091479689106,
    "score_high": 58.09003241411621,
    "mean_cost_usd_per_task": 1.1343762765486725,
    "median_cost_usd_per_task": 1.031709,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:900c8577e3bc443d",
    "variant": "mini-swe-agent - gpt-5-6-terra (medium)",
    "score": 35.11111111111111,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 31.729146807704478,
    "score_high": 38.49307541451774,
    "mean_cost_usd_per_task": 0.5832493688888889,
    "median_cost_usd_per_task": 0.546099,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:329cf994aaf09cfd",
    "variant": "mini-swe-agent - gpt-5-6-terra (low)",
    "score": 24.053452115812917,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 23.276690748868134,
    "score_high": 24.830213482757703,
    "mean_cost_usd_per_task": 0.4277452605790646,
    "median_cost_usd_per_task": 0.3989895,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:a795ed51d673418d",
    "variant": "Gemini 3.8 Flash (high)",
    "score": 40.9262,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8f226080bd0bde9a",
    "variant": "Gemini 3.8 Flash (medium)",
    "score": 39.774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e0b41460917d3eff",
    "variant": "Gemini 3.8 Flash (low)",
    "score": 33.4548,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:206ddf92cd474c5f",
    "variant": "mini-SWE-agent - Gemini 3.8 Flash (high)",
    "score": 19.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 15.73,
    "score_high": 22.45,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a1eae5d167a32a34",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (medium)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a0853cb96c8ece1",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (high)",
    "score": 19.697,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:76b42aa2f87efd5c",
    "variant": "Artificial Analysis - Gemini 3.8 Flash (low)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:cee78179b654f666",
    "variant": "gemini-3.8-flash-high",
    "score": 1583,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1575.1,
    "score_high": 1590.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:60a00778bc1492a5",
    "variant": "Gemini 3.8 Flash (High)",
    "score": 2.96,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 2.14,
    "score_high": 3.78,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.58,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:68de21286728c605",
    "variant": "Antigravity SDK - Gemini 3.8 Flash (high)",
    "score": 41.8632,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Antigravity SDK v0.1.12",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 2.4674,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:e5b1ca76e59dabd0",
    "variant": "Gemini 3.8 Flash",
    "score": 68.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.210201,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a4e0e06e8292b616",
    "variant": "mini-swe-agent - gemini-3-8-flash (high)",
    "score": 73.8255033557047,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 72.40819014906883,
    "score_high": 75.24281656234058,
    "mean_cost_usd_per_task": 2.362349413758389,
    "median_cost_usd_per_task": 2.1098912999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.8-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9fafa3956afdc304",
    "variant": "mini-swe-agent - gemini-3-8-flash (medium)",
    "score": 71.01769911504425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 68.73689454216633,
    "score_high": 73.29850368792218,
    "mean_cost_usd_per_task": 1.9671024789823006,
    "median_cost_usd_per_task": 1.7342966249999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:59269287bc1e95d8",
    "variant": "Gemini 3.7 Flash (medium) [AA estimate]",
    "score": 39.6178,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:aeabf6017dd74bc8",
    "variant": "Gemini 3.7 Flash (high)",
    "score": 39.0595,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cc014f66e9d183e0",
    "variant": "Gemini 3.7 Flash (low) [AA estimate]",
    "score": 36.9459,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2106790cd4627629",
    "variant": "mini-SWE-agent - Gemini 3.7 Flash (high)",
    "score": 11.21,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-SWE-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 8.760000000000002,
    "score_high": 13.66,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69dd3b76427af507",
    "variant": "Artificial Analysis - Gemini 3.7 Flash (high)",
    "score": 13.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:778f5c97eb827e03",
    "variant": "gemini-3.7-flash-high",
    "score": 1592,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1584.6,
    "score_high": 1599.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:47cad90e68374509",
    "variant": "Gemini 3.7 Flash (High)",
    "score": -1.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -2.4,
    "score_high": -0.8799999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e9d8d5305f3c7552",
    "variant": "mini-swe-agent - gemini-3-7-flash (medium)",
    "score": 65.48672566371681,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 62.40019338730129,
    "score_high": 68.57325794013234,
    "mean_cost_usd_per_task": 2.0251351826880533,
    "median_cost_usd_per_task": 1.65422055,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a62d7ab2cd07619d",
    "variant": "mini-swe-agent - gemini-3-7-flash (high)",
    "score": 65.2654867256637,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.47762421887939,
    "score_high": 67.05334923244803,
    "mean_cost_usd_per_task": 2.1762860351216813,
    "median_cost_usd_per_task": 1.9044440625,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::gemini-3.7-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c3c0d085a762f3d1",
    "variant": "mini-swe-agent - gemini-3-7-flash (low)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 51.171412865070785,
    "score_high": 56.35071102873452,
    "mean_cost_usd_per_task": 1.8322645629424779,
    "median_cost_usd_per_task": 1.3913454375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::inkling",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ae97bbe112769bcd",
    "variant": "Inkling (xhigh)",
    "score": 24.9848,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::inkling",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8b8fcc0fa14e07eb",
    "variant": "Artificial Analysis - Inkling (xhigh)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::inkling",
    "board": "arena_code",
    "configuration_id": "arena_code:07b745ae2862d994",
    "variant": "inkling",
    "score": 1412,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1405.6,
    "score_high": 1418.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::inkling",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8967f33635820f8b",
    "variant": "Inkling",
    "score": -10.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -11.96,
    "score_high": -9.84,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.25,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::mistral-medium-3.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:479a072abc28cf2a",
    "variant": "Mistral Medium 3.5",
    "score": 14.1889,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::mistral-medium-3.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:d8495a02281ad221",
    "variant": "Artificial Analysis - Mistral Medium 3.5",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::mistral-medium-3.5",
    "board": "arena_code",
    "configuration_id": "arena_code:daa8896f14bb8dc8",
    "variant": "mistral-medium-3.5",
    "score": 1263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 1248.2,
    "score_high": 1277.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::mistral-medium-3.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9c4432eeedad5bad",
    "variant": "Mistral Medium 3.5",
    "score": -11.74,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": -13.24,
    "score_high": -10.24,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.67,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:066a860a43b7204e",
    "variant": "GLM-5.3-Flash",
    "score": 41.8075,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:458e21cad837a439",
    "variant": "Artificial Analysis - GLM-5.3-Flash",
    "score": 32.8283,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:379b30f1d5942d86",
    "variant": "glm-5.3-flash",
    "score": 1615,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1607.3,
    "score_high": 1622.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:bd0ff69aca5acca9",
    "variant": "GLM 5.3 Flash",
    "score": -0.28,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -0.76,
    "score_high": 0.19999999999999996,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.1,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:2bf6b5cf8d0df775",
    "variant": "mini-swe-agent - glm-5-3-flash (max)",
    "score": 63.39285714285714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 59.0148863911635,
    "score_high": 67.77082789455078,
    "mean_cost_usd_per_task": 0.48196371245535713,
    "median_cost_usd_per_task": 0.389975125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:21922ac966701739",
    "variant": "GLM-5.3 (max)",
    "score": 44.7774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:237ff152b6aa847d",
    "variant": "GLM-5.3 (low)",
    "score": 34.299,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0bfd0655b217cb23",
    "variant": "Claude Code - GLM-5.3 (max)",
    "score": 41.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 38.59,
    "score_high": 45.05,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:496fda38cce0cdb6",
    "variant": "Artificial Analysis - GLM-5.3 (max)",
    "score": 41.9192,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:69eafd0d76477763",
    "variant": "Artificial Analysis - GLM-5.3 (low)",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "arena_code",
    "configuration_id": "arena_code:2d279d541bee2ba7",
    "variant": "glm-5.3-max",
    "score": 1622,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1613.8,
    "score_high": 1630.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:64885804c8dddecd",
    "variant": "GLM 5.3 (Max)",
    "score": 2.57,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1.8499999999999999,
    "score_high": 3.29,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.64,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:9f41ae70311c2b0b",
    "variant": "Opencode - GLM-5.3",
    "score": 53.5548,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Opencode",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 4.2414,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:dac434c8397694b1",
    "variant": "mini-swe-agent - glm-5-3 (max)",
    "score": 68.95787139689578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.93922012533709,
    "score_high": 71.97652266845449,
    "mean_cost_usd_per_task": 3.9933584893126386,
    "median_cost_usd_per_task": 3.1315945999999992,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4b9229f7a5210ab7",
    "variant": "GLM-5.2 (max)",
    "score": 33.7055,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bf6c2c604a56c9d0",
    "variant": "GLM-5.2 (non-reasoning) [AA estimate]",
    "score": 22.4323,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9ad8c75e6b68658f",
    "variant": "Artificial Analysis - GLM-5.2 (max)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "arena_code",
    "configuration_id": "arena_code:828ee7654a1873aa",
    "variant": "glm-5.2-max",
    "score": 1605,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1598.6,
    "score_high": 1611.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:f4f60f98940c49ee",
    "variant": "GLM 5.2 (Max)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.9000000000000004,
    "score_high": 4.38,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.76,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3c0de09601f2c8a8",
    "variant": "mini-swe-agent - glm-5-2 (max)",
    "score": 43.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 42.05214815719697,
    "score_high": 45.50340739835859,
    "mean_cost_usd_per_task": 3.9199075743111114,
    "median_cost_usd_per_task": 3.4637479200000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::glm-5.2",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:71a3c9c8333b9bfd",
    "variant": "mini-swe-agent - glm-5-2 (high)",
    "score": 36.283185840707965,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 31.533112892786306,
    "score_high": 41.033258788629624,
    "mean_cost_usd_per_task": 2.8355164725663715,
    "median_cost_usd_per_task": 2.25012998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13115cf53ac21275",
    "variant": "Kimi K3 (max)",
    "score": 43.5938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:50501b171b1855d0",
    "variant": "Kimi K3 (low)",
    "score": 30.0667,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:cc7c150caad9b305",
    "variant": "Artificial Analysis - Kimi K3 (low)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a6ac642cac2ac396",
    "variant": "Artificial Analysis - Kimi K3 (max)",
    "score": 12.6263,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "arena_code",
    "configuration_id": "arena_code:ac2bf8a87d9de607",
    "variant": "kimi-k3-max",
    "score": 1658,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1651.6,
    "score_high": 1664.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:1307216843d89276",
    "variant": "Kimi K3 (Max)",
    "score": 3.98,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.45,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.75,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:4a7256426ed97ee6",
    "variant": "Kimi Code CLI - Kimi K3",
    "score": 51.9259,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Kimi Code CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 5.0472,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:9aadc4d724514f03",
    "variant": "Kimi K3",
    "score": 65.7,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.613653,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::kimi-k3",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:aefa4afd042df82c",
    "variant": "mini-swe-agent - kimi-k3 (max)",
    "score": 68.51441241685144,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.97739833756913,
    "score_high": 73.05142649613376,
    "mean_cost_usd_per_task": 4.654682129933482,
    "median_cost_usd_per_task": 3.6024987,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8919405f90e7565f",
    "variant": "Qwen3.8 Max",
    "score": 40.1529,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0487a0a408dccb82",
    "variant": "Artificial Analysis - Qwen3.8 Max",
    "score": 18.6869,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "arena_code",
    "configuration_id": "arena_code:ab7cf4e12f67d532",
    "variant": "qwen3.8-max",
    "score": 1671,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1659.0,
    "score_high": 1683.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:9ce366a4c245bae4",
    "variant": "Qwen3.8 Max",
    "score": 2.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 2.15,
    "score_high": 3.4499999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:82bc37b4bd5aa375",
    "variant": "Claude Code - Qwen3.8 Max",
    "score": 43.2653,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.479,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:fbd3d33fa1d7cf9a",
    "variant": "Qwen 3.8-Max",
    "score": 72,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.595399,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::qwen3.8-max",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f20515f2e81cba89",
    "variant": "mini-swe-agent - qwen3-8-max (xhigh)",
    "score": 57.46102449888642,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.798231826378874,
    "score_high": 60.12381717139396,
    "mean_cost_usd_per_task": 3.7290646500445437,
    "median_cost_usd_per_task": 3.132689060000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::nemotron-3-ultra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5cd72513bff7d4b7",
    "variant": "Nemotron 3 Ultra",
    "score": 22.9279,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::nemotron-3-ultra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:3d0d41d5c6a6aa9b",
    "variant": "Artificial Analysis - Nemotron 3 Ultra",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::minimax-m3",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:179c62d659734cb1",
    "variant": "MiniMax-M3",
    "score": 29.2203,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::minimax-m3",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4f6bf2d4de391fa8",
    "variant": "Artificial Analysis - MiniMax-M3",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::minimax-m3",
    "board": "arena_code",
    "configuration_id": "arena_code:f206c3043bc8027f",
    "variant": "minimax-m3",
    "score": 1482,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1476.3,
    "score_high": 1487.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "droid_max::minimax-m3",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:a16fe8d7c7b78883",
    "variant": "Minimax M3",
    "score": -6.71,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": -7.6,
    "score_high": -5.82,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.08,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_cn::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m2.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:58eba7a1df2c56c5",
    "variant": "MiniMax-M2.7",
    "score": 22.7578,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m2.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ba9180d8eb1c0d7",
    "variant": "Artificial Analysis - MiniMax-M2.7",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "minimax_token_plus_global::minimax-m2.7",
    "board": "arena_code",
    "configuration_id": "arena_code:891df129a594a41e",
    "variant": "minimax-m2.7",
    "score": 1397,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1391.2,
    "score_high": 1402.8,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "devin_pro::swe-2",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:1852bc281e1867f4",
    "variant": "Devin CLI - SWE-2 (best effort) [vendor self-report]",
    "score": 27.3,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Devin CLI",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://cognition.com/blog/swe-2",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_offpeak::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:8076c0cba16368e2",
    "variant": "DeepSeek V4.1 Flash (max)",
    "score": 39.4562,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d81376edf86feffa",
    "variant": "DeepSeek V4.1 Flash (non-reasoning)",
    "score": 24.6734,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:b14874c72f248246",
    "variant": "DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 31.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "DeepSeek Harness Minimal",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1e5a05b16aa7028a",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (max)",
    "score": 26.7677,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5b3cd3f66e09bf91",
    "variant": "Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning)",
    "score": 5.5556,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:4e5d5fbc5aef2e52",
    "variant": "deepseek-v4.1-flash-max",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1609.6,
    "score_high": 1630.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:c8965e5dd2526f05",
    "variant": "Deepseek V4.1 Flash (Max)",
    "score": 4.01,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 3.51,
    "score_high": 4.51,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.09,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:050e7234636e98be",
    "variant": "DeepSeek V4.1 Flash",
    "score": 81.2,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.023264,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v41_flash_peak::deepseek-v4.1-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3d9b43ea1f40d6be",
    "variant": "mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report]",
    "score": 74.2,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-SWE",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_offpeak::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b6a092361e695dd6",
    "variant": "DeepSeek V4 Flash 0731 (max)",
    "score": 34.3305,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7cb5e674535a254b",
    "variant": "DeepSeek V4 Flash (high)",
    "score": 24.384,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:db4df116f5cc1c83",
    "variant": "DeepSeek V4 Flash (max)",
    "score": 24.1673,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:610f4083dbb622ce",
    "variant": "DeepSeek V4 Flash (non-reasoning) [AA estimate]",
    "score": 18.8769,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a807bd1873a40322",
    "variant": "Artificial Analysis - DeepSeek V4 Flash 0731 (max)",
    "score": 12.1212,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a2b58faa52397cc0",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (high)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:fee6e8fd477b7ac8",
    "variant": "Artificial Analysis - DeepSeek V4 Flash (max)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:672fd54eff364145",
    "variant": "deepseek-v4-flash-high",
    "score": 1581,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1571.8,
    "score_high": 1590.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "arena_code",
    "configuration_id": "arena_code:f3628e90994fda44",
    "variant": "deepseek-v4-flash-high-preview",
    "score": 1430,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1423.1,
    "score_high": 1436.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:77cf38495a1886a0",
    "variant": "Codex - DeepSeek V4 Flash 0731 (max)",
    "score": 38.7425,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.0851,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_flash_peak::deepseek-v4-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c0668bd778ebe124",
    "variant": "mini-swe-agent - deepseek-v4-flash (max)",
    "score": 53.31858407079646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.751633855764034,
    "score_high": 56.88553428582889,
    "mean_cost_usd_per_task": 0.10023560370265487,
    "median_cost_usd_per_task": 0.09124898719999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_offpeak::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e551b2b658c831ff",
    "variant": "DeepSeek V4 Pro 0813 (max)",
    "score": 35.9968,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:99ded62ad6efb9a5",
    "variant": "DeepSeek V4 Pro (max)",
    "score": 30.4497,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:1635385ef12eb561",
    "variant": "DeepSeek V4 Pro (high) [AA estimate]",
    "score": 30.1055,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e15aa3daea8ed086",
    "variant": "DeepSeek V4 Pro (non-reasoning) [AA estimate]",
    "score": 20.8345,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:f323daf280bfff22",
    "variant": "DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 20.3605,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:c2972229b7214dfc",
    "variant": "Artificial Analysis - DeepSeek V4 Pro (max)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:92c8207e8ca30249",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79eac9decde86827",
    "variant": "Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:986ec1bc7da59bd9",
    "variant": "deepseek-v4-pro-high-20260813",
    "score": 1582,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1572.7,
    "score_high": 1591.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:e98573cb34bd81ce",
    "variant": "deepseek-v4-pro-high-preview",
    "score": 1463,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1456.7,
    "score_high": 1469.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:fec2568cdfba26c6",
    "variant": "deepseek-v4-pro",
    "score": 1446,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1439.7,
    "score_high": 1452.3,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3081d8b084b897bf",
    "variant": "DeepSeek V4 Pro (High) (0813)",
    "score": 1.29,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": -0.4099999999999999,
    "score_high": 2.99,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.38,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d18f5779019b6787",
    "variant": "Codex - DeepSeek V4 Pro 0813 (max)",
    "score": 43.052,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.238,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "deepseek_v4_pro_peak::deepseek-v4-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b317c65fa31ed642",
    "variant": "mini-swe-agent - deepseek-v4-pro (max)",
    "score": 62.83185840707964,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 56.49842780985077,
    "score_high": 69.16528900430852,
    "mean_cost_usd_per_task": 0.24138687892256638,
    "median_cost_usd_per_task": 0.2232531505000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c95dc5141f32b497",
    "variant": "GPT-5.6 Sol (max)",
    "score": 46.9727,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:467034ea7730fe43",
    "variant": "GPT-5.6 Sol (xhigh)",
    "score": 44.0089,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5b0f75c30f0ab19b",
    "variant": "GPT-5.6 Sol (high)",
    "score": 42.3461,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:64efdbd82ca66394",
    "variant": "GPT-5.6 Sol (medium)",
    "score": 39.2364,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d1b16dee33968223",
    "variant": "GPT-5.6 Sol (low)",
    "score": 33.4731,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:15f1554828f5b0dc",
    "variant": "GPT-5.6 Sol (non-reasoning) [AA estimate]",
    "score": 28.328,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:52ccc5571264dbe4",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 37.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 33.49,
    "score_high": 41.050000000000004,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:7ac4c013fed0b565",
    "variant": "Artificial Analysis - GPT-5.6 Sol (max)",
    "score": 39.899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f850c291e94d4eee",
    "variant": "Artificial Analysis - GPT-5.6 Sol (xhigh)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f0f6b217be9a4963",
    "variant": "Artificial Analysis - GPT-5.6 Sol (high)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:de8c4cd8b48f6964",
    "variant": "Artificial Analysis - GPT-5.6 Sol (medium)",
    "score": 14.6465,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a5ddeab611927928",
    "variant": "Artificial Analysis - GPT-5.6 Sol (low)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "arena_code",
    "configuration_id": "arena_code:7e9fde485c6ddc62",
    "variant": "gpt-5.6-sol-xhigh (codex-harness)",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1613.0,
    "score_high": 1625.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5c55fe7f551fe2c6",
    "variant": "GPT 5.6 Sol (xHigh)",
    "score": 7.05,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 5.67,
    "score_high": 8.43,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.05,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:538ede13f4f0982c",
    "variant": "Codex - GPT-5.6 Sol (max)",
    "score": 54.5591,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 6.3533,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:048a6b75c77d30fe",
    "variant": "GPT-5.6 Sol",
    "score": 77.6,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.544242,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b7fe36ffe2e53058",
    "variant": "mini-swe-agent - gpt-5-6-sol (max)",
    "score": 72.66666666666667,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.83684441682949,
    "score_high": 75.49648891650385,
    "mean_cost_usd_per_task": 8.386436346666667,
    "median_cost_usd_per_task": 6.8414715,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:20ba110314745668",
    "variant": "mini-swe-agent - gpt-5-6-sol (xhigh)",
    "score": 70.73170731707317,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 69.91259559533886,
    "score_high": 71.55081903880748,
    "mean_cost_usd_per_task": 4.703663860310422,
    "median_cost_usd_per_task": 4.117039,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:b9f6b563ece4cecf",
    "variant": "mini-swe-agent - gpt-5-6-sol (high)",
    "score": 69.40133037694012,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.9691851565629,
    "score_high": 70.83347559731736,
    "mean_cost_usd_per_task": 3.4698331108647453,
    "median_cost_usd_per_task": 2.979421,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:d0270ad29cebc03b",
    "variant": "mini-swe-agent - gpt-5-6-sol (medium)",
    "score": 61.06194690265486,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 59.47858925334765,
    "score_high": 62.64530455196208,
    "mean_cost_usd_per_task": 1.8620318075221238,
    "median_cost_usd_per_task": 1.545414,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_sol_api::gpt-5.6-sol",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:eed6875ca51165fd",
    "variant": "mini-swe-agent - gpt-5-6-sol (low)",
    "score": 45.35398230088495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 42.96578762942603,
    "score_high": 47.74217697234388,
    "mean_cost_usd_per_task": 1.0742664646017699,
    "median_cost_usd_per_task": 0.944557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b56103ded435971f",
    "variant": "Grok 4.6 (high)",
    "score": 44.3113,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:13ecd3c1725d233e",
    "variant": "Grok 4.6 (xhigh)",
    "score": 44.1998,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2df81011d518b272",
    "variant": "Grok 4.6 (medium)",
    "score": 42.8363,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2e9f902e3fc120db",
    "variant": "Grok 4.6 (low)",
    "score": 35.1247,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:2c30600255377a7d",
    "variant": "Grok Build - Grok 4.6 (high)",
    "score": 20.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 17.21,
    "score_high": 23.39,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0493139313b0b012",
    "variant": "Artificial Analysis - Grok 4.6 (high)",
    "score": 21.2121,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:27d67549b5ee1d8d",
    "variant": "Artificial Analysis - Grok 4.6 (xhigh)",
    "score": 17.1717,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:008592dee2abfbd4",
    "variant": "Artificial Analysis - Grok 4.6 (medium)",
    "score": 13.1313,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:ab17cc8e5487de99",
    "variant": "Artificial Analysis - Grok 4.6 (low)",
    "score": 3.0303,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "arena_code",
    "configuration_id": "arena_code:dec9c8da0773c02d",
    "variant": "grok-4.6-high",
    "score": 1620,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1612.1,
    "score_high": 1627.9,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:09fac21036f59279",
    "variant": "Grok 4.6 (xHigh)",
    "score": 1.16,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 0.1399999999999999,
    "score_high": 2.1799999999999997,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.99,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1157285386872e0a",
    "variant": "Grok Build - Grok 4.6 (xhigh)",
    "score": 46.969,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.5701,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9517554a020a7af3",
    "variant": "mini-swe-agent - grok-4-6 (medium)",
    "score": 67.47787610619469,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 65.19707153331677,
    "score_high": 69.7586806790726,
    "mean_cost_usd_per_task": 3.4489837522123894,
    "median_cost_usd_per_task": 2.945834,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:017a7f4c8bf6ada0",
    "variant": "mini-swe-agent - grok-4-6 (xhigh)",
    "score": 66.74057649667405,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 64.564892272269,
    "score_high": 68.9162607210791,
    "mean_cost_usd_per_task": 5.497668745011087,
    "median_cost_usd_per_task": 4.63937,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6c1cc54c4677acba",
    "variant": "mini-swe-agent - grok-4-6 (high)",
    "score": 65.18847006651885,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 63.65486924786155,
    "score_high": 66.72207088517614,
    "mean_cost_usd_per_task": 4.3848732239467845,
    "median_cost_usd_per_task": 3.693604,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok46_api::grok-4.6",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:baca3e04439efe09",
    "variant": "mini-swe-agent - grok-4-6 (low)",
    "score": 41.648106904231625,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.32945513980172,
    "score_high": 43.96675866866153,
    "mean_cost_usd_per_task": 1.0423604231625836,
    "median_cost_usd_per_task": 0.742614,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d11843ec849da6d9",
    "variant": "Grok 4.7 (xhigh)",
    "score": 46.4466,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:0c727f941b7eae61",
    "variant": "Grok 4.7 (high)",
    "score": 46.3322,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:bb8c22faf493862e",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 37.58,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 34.04,
    "score_high": 41.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:24968b82abf21817",
    "variant": "Artificial Analysis - Grok 4.7 (xhigh)",
    "score": 25.7576,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:131082f722734b10",
    "variant": "Artificial Analysis - Grok 4.7 (high)",
    "score": 24.7475,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "arena_code",
    "configuration_id": "arena_code:168968cc57cebb7d",
    "variant": "grok-4.7-xhigh",
    "score": 1636,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1624.0,
    "score_high": 1648.0,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:0684f9cc2a945bdb",
    "variant": "Grok 4.7 (xHigh)",
    "score": 3.64,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 2.0700000000000003,
    "score_high": 5.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.47,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:fa75b2e79a4d8cb4",
    "variant": "Grok Build - Grok 4.7 (xhigh)",
    "score": 56.2676,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Grok Build",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 8.8175,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:91957ddea79bc27b",
    "variant": "Grok 4.7",
    "score": 82.9,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.662291,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "xai_grok47_api::grok-4.7",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1d433900eaa0bee0",
    "variant": "mini-swe-agent - grok-4-7 (high) [vendor self-report]",
    "score": 71.0,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://x.ai/news/grok-4-7",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_pro_api::mimo-v2.6-pro",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:83bd852b96aedbce",
    "variant": "MiMo-V2.6-Pro",
    "score": 46.3242,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_pro_api::mimo-v2.6-pro",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b5691a8df0db5041",
    "variant": "Artificial Analysis - MiMo-V2.6-Pro",
    "score": 34.8485,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_pro_api::mimo-v2.6-pro",
    "board": "arena_code",
    "configuration_id": "arena_code:8f9ded4c04cd93a8",
    "variant": "mimo-v2.6-pro",
    "score": 1619,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": 1606.8,
    "score_high": 1631.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_pro_api::mimo-v2.6-pro",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:9454d8de1c52f2fc",
    "variant": "mini-swe-agent - mimo-v2-6-pro [vendor self-report]",
    "score": 71.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_flash_api::mimo-v2.6-flash",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2446e4ad7216a14c",
    "variant": "MiMo-V2.6-Flash",
    "score": 37.8844,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_flash_api::mimo-v2.6-flash",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f1477201d34edbb5",
    "variant": "Artificial Analysis - MiMo-V2.6-Flash",
    "score": 22.7273,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_flash_api::mimo-v2.6-flash",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:af24dbf7d52582a5",
    "variant": "MiMo 2.6 Flash",
    "score": 83.5,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.02894,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "mimo_v26_flash_api::mimo-v2.6-flash",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:c2b10fcdefbd0221",
    "variant": "mini-swe-agent - mimo-v2-6-flash [vendor self-report]",
    "score": 67.9,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:68425237e9876779",
    "variant": "Claude Opus 5 (max)",
    "score": 50.7771,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3a154cb4e9c99189",
    "variant": "Claude Opus 5 (xhigh)",
    "score": 49.6774,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:295f5f7bdfa8d248",
    "variant": "Claude Opus 5 (high)",
    "score": 48.1219,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:bacfec5f5f91d13c",
    "variant": "Claude Opus 5 (medium)",
    "score": 44.8253,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e42133cf9100a842",
    "variant": "Claude Opus 5 (low)",
    "score": 39.3543,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7d59ed14e6a26f29",
    "variant": "Claude Code - Opus 5 (xhigh)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 50.769999999999996,
    "score_high": 57.11,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cec3b7db483cca26",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 51.82,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 48.43,
    "score_high": 55.21,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:82e30cded058a067",
    "variant": "Claude Code - Opus 5 (high)",
    "score": 50.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 46.57,
    "score_high": 54.029999999999994,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:314e4521dd78b2f2",
    "variant": "Claude Code - Opus 5 (medium)",
    "score": 44.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 41.02,
    "score_high": 48.68,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:3ef9fcfb65e0cb76",
    "variant": "Claude Code - Opus 5 (low)",
    "score": 34.85,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 30.91,
    "score_high": 38.79,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0ed48e92962897a4",
    "variant": "Artificial Analysis - Claude Opus 5 (max)",
    "score": 48.9899,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0838ca37e5fa42da",
    "variant": "Artificial Analysis - Claude Opus 5 (xhigh)",
    "score": 46.4646,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8e10956f03aaa14d",
    "variant": "Artificial Analysis - Claude Opus 5 (high)",
    "score": 45.9596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:314fe657e048e298",
    "variant": "Artificial Analysis - Claude Opus 5 (medium)",
    "score": 34.3434,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a61fb5355f7888c8",
    "variant": "Artificial Analysis - Claude Opus 5 (low)",
    "score": 26.2626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:3aa3e36faa602970",
    "variant": "claude-opus-5-max",
    "score": 1694,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1687.5,
    "score_high": 1700.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "arena_code",
    "configuration_id": "arena_code:6b8714542169429d",
    "variant": "claude-opus-5-high",
    "score": 1660,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1654.3,
    "score_high": 1665.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:63ab115851e0de58",
    "variant": "Claude Opus 5 (High)",
    "score": 8.76,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.26,
    "score_high": 10.26,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.5,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:7b426212aba5971e",
    "variant": "Claude Opus 5 (Max)",
    "score": 8.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 6.98,
    "score_high": 10.120000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 3.59,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:e0b71dfaa4f1714e",
    "variant": "Claude Code - Opus 5 (max)",
    "score": 59.7264,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 10.7892,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:f029cafdaf0a4ee3",
    "variant": "mini-swe-agent - claude-opus-5 (max)",
    "score": 73.64864864864865,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 69.77633822227692,
    "score_high": 77.52095907502039,
    "mean_cost_usd_per_task": 11.837583271396396,
    "median_cost_usd_per_task": 10.4281505,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:853cb17f0e600556",
    "variant": "mini-swe-agent - claude-opus-5 (xhigh)",
    "score": 73.15436241610739,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 70.09338059446893,
    "score_high": 76.21534423774585,
    "mean_cost_usd_per_task": 9.07220232326622,
    "median_cost_usd_per_task": 7.928816750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e252d58fa6da2ebe",
    "variant": "mini-swe-agent - claude-opus-5 (high)",
    "score": 72.82850779510022,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 70.88307563794007,
    "score_high": 74.77393995226038,
    "mean_cost_usd_per_task": 6.076084489977728,
    "median_cost_usd_per_task": 4.96882375,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:df5db3bddc1856ee",
    "variant": "mini-swe-agent - claude-opus-5 (medium)",
    "score": 68.90380313199105,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 67.73124446609795,
    "score_high": 70.07636179788415,
    "mean_cost_usd_per_task": 3.28978764541387,
    "median_cost_usd_per_task": 2.4819885000000004,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus5_api::claude-opus-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3353f4eaaecc0e42",
    "variant": "mini-swe-agent - claude-opus-5 (low)",
    "score": 58.12917594654788,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 55.79848799986361,
    "score_high": 60.45986389323216,
    "mean_cost_usd_per_task": 1.6626223919821828,
    "median_cost_usd_per_task": 1.2162672499999996,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:00e5e17098f2a9cc",
    "variant": "Claude Sonnet 5 (max)",
    "score": 38.1639,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:26fc619ae9c44efb",
    "variant": "Claude Sonnet 5 (xhigh)",
    "score": 34.3842,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:c089bab844997713",
    "variant": "Claude Sonnet 5 (high)",
    "score": 31.6623,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2b12f7c3563de350",
    "variant": "Claude Sonnet 5 (medium)",
    "score": 28.0531,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b99819b727eb71df",
    "variant": "Claude Sonnet 5 (low)",
    "score": 24.2638,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:e35c69aedd168116",
    "variant": "Claude Sonnet 5 (non-reasoning) [AA estimate]",
    "score": 23.2,
    "score_is_estimated": true,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5718a86e9278cdf2",
    "variant": "Claude Code - Sonnet 5 (max)",
    "score": 12.42,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 9.36,
    "score_high": 15.48,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8a2bf906a5cca32e",
    "variant": "Artificial Analysis - Claude Sonnet 5 (max)",
    "score": 14.1414,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:58f8a2ad361cbfac",
    "variant": "Artificial Analysis - Claude Sonnet 5 (xhigh)",
    "score": 7.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4583c02c014dc3d1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (high)",
    "score": 5.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:0a46e136780aeec1",
    "variant": "Artificial Analysis - Claude Sonnet 5 (low)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:eecd341c62332c35",
    "variant": "Artificial Analysis - Claude Sonnet 5 (medium)",
    "score": 2.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "arena_code",
    "configuration_id": "arena_code:c91ce134bd5ec2e3",
    "variant": "claude-sonnet-5-high",
    "score": 1540,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1533.8,
    "score_high": 1546.2,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:5729b5a20a335dfc",
    "variant": "Claude Sonnet 5 (High)",
    "score": 4.81,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 3.09,
    "score_high": 6.529999999999999,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.9,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:17f1ccadd79e3f73",
    "variant": "mini-swe-agent - claude-sonnet-5 (max)",
    "score": 53.84615384615385,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 49.60923737597946,
    "score_high": 58.08307031632823,
    "mean_cost_usd_per_task": 26.399858950791852,
    "median_cost_usd_per_task": 23.277376725000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:6a089e055d07f388",
    "variant": "mini-swe-agent - claude-sonnet-5 (xhigh)",
    "score": 49.667405764966745,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 46.21285677328888,
    "score_high": 53.121954756644605,
    "mean_cost_usd_per_task": 11.890634540022173,
    "median_cost_usd_per_task": 9.965361750000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e833a890e9fc6ef0",
    "variant": "mini-swe-agent - claude-sonnet-5 (high)",
    "score": 48.23008849557522,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 43.72377362536038,
    "score_high": 52.73640336579006,
    "mean_cost_usd_per_task": 7.425560161197339,
    "median_cost_usd_per_task": 5.833649100000001,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:3cee9c2890b172bc",
    "variant": "mini-swe-agent - claude-sonnet-5 (medium)",
    "score": 39.77777777777778,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 36.65020157144805,
    "score_high": 42.90535398410751,
    "mean_cost_usd_per_task": 4.079036229,
    "median_cost_usd_per_task": 3.3573110999999995,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet5_api::claude-sonnet-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:4b4fac04da320c00",
    "variant": "mini-swe-agent - claude-sonnet-5 (low)",
    "score": 30.51224944320713,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 29.386231901764383,
    "score_high": 31.638266984649878,
    "mean_cost_usd_per_task": 2.1865550832962137,
    "median_cost_usd_per_task": 1.6764955500000003,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9b5f20f46c907550",
    "variant": "Claude Fable 5 (with fallback)",
    "score": 49.6258,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:eb2874e55b9e0003",
    "variant": "Claude Code - Fable 5 (max)",
    "score": 44.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 40.699999999999996,
    "score_high": 48.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:6fd65552e1fc1e0a",
    "variant": "Artificial Analysis - Claude Fable 5 (with fallback)",
    "score": 42.4242,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "arena_code",
    "configuration_id": "arena_code:72ebbd507122c58e",
    "variant": "claude-fable-5-high",
    "score": 1626,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1619.6,
    "score_high": 1632.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:3d3ae04ef0c99602",
    "variant": "Claude Fable 5 (High)",
    "score": 8.37,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 7.069999999999999,
    "score_high": 9.67,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 2.02,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:60791be82ce959e0",
    "variant": "mini-swe-agent - claude-fable-5 (xhigh)",
    "score": 69.91150442477876,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 66.66658684930744,
    "score_high": 73.15642200025007,
    "mean_cost_usd_per_task": 13.414521495535714,
    "median_cost_usd_per_task": 11.341082999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:e5e5c5b317b1f68a",
    "variant": "mini-swe-agent - claude-fable-5 (max)",
    "score": 69.72477064220183,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 65.6912963913939,
    "score_high": 73.75824489300977,
    "mean_cost_usd_per_task": 21.634702092592594,
    "median_cost_usd_per_task": 19.23457225,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:42fd11a99a8570ba",
    "variant": "mini-swe-agent - claude-fable-5 (high)",
    "score": 68.6046511627907,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 67.48380844536031,
    "score_high": 69.7254938802211,
    "mean_cost_usd_per_task": 9.177638214788733,
    "median_cost_usd_per_task": 7.322686000000002,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:a1709ab0b129e07e",
    "variant": "mini-swe-agent - claude-fable-5 (medium)",
    "score": 65.36697247706422,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 60.94504359782606,
    "score_high": 69.78890135630239,
    "mean_cost_usd_per_task": 6.088186528935186,
    "median_cost_usd_per_task": 4.62221125,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable5_api::claude-fable-5",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:53874601b1d3b3da",
    "variant": "mini-swe-agent - claude-fable-5 (low)",
    "score": 59.58429561200924,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 56.79029016687951,
    "score_high": 62.37830105713898,
    "mean_cost_usd_per_task": 3.757873125874126,
    "median_cost_usd_per_task": 2.7559204999999998,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:71823637d973a0fc",
    "variant": "Claude Fable 5.1 (max with fallback)",
    "score": 53.3549,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:3f66aafbb8812925",
    "variant": "Claude Fable 5.1 (xhigh with fallback)",
    "score": 53.2033,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:74265ef58fb6e45b",
    "variant": "Claude Fable 5.1 (high with fallback)",
    "score": 51.1516,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:9a927f4404e32355",
    "variant": "Claude Fable 5.1 (medium with fallback)",
    "score": 48.9206,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:2ceeec877967a38a",
    "variant": "Claude Fable 5.1 (low with fallback)",
    "score": 46.8163,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:136537b36ce98c25",
    "variant": "Claude Code - Fable 5.1 (max)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 54.120000000000005,
    "score_high": 61.64,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:cc67912665adccef",
    "variant": "Claude Code - Fable 5.1 (xhigh)",
    "score": 57.88,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.52,
    "score_high": 61.24,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:c1be8fa31509c696",
    "variant": "Claude Code - Fable 5.1 (high)",
    "score": 54.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 51.11,
    "score_high": 57.989999999999995,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:5edd3a6853cd6339",
    "variant": "Claude Code - Fable 5.1 (medium)",
    "score": 53.94,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 50.55,
    "score_high": 57.33,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:4bcb6aba27442f07",
    "variant": "Claude Code - Fable 5.1 (low)",
    "score": 43.33,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 39.72,
    "score_high": 46.94,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:41e12ce515ec9121",
    "variant": "Artificial Analysis - Claude Fable 5.1 (xhigh with fallback)",
    "score": 55.0505,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1512d68b0eb6bc1b",
    "variant": "Artificial Analysis - Claude Fable 5.1 (max with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e606b01ceda846f9",
    "variant": "Artificial Analysis - Claude Fable 5.1 (high with fallback)",
    "score": 52.0202,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:93ccfc6e6c1f4910",
    "variant": "Artificial Analysis - Claude Fable 5.1 (medium with fallback)",
    "score": 44.9495,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:5e01b08628a88aac",
    "variant": "Artificial Analysis - Claude Fable 5.1 (low with fallback)",
    "score": 40.404,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "arena_code",
    "configuration_id": "arena_code:8e70472a84bf71d1",
    "variant": "claude-fable-5.1-max",
    "score": 1751,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1741.3,
    "score_high": 1760.7,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:d1cdd70383ae2039",
    "variant": "Claude Fable 5.1 (Max)",
    "score": 14.55,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 12.63,
    "score_high": 16.47,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 4.44,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:f882189259104e87",
    "variant": "Claude Code - Fable 5.1 (max) (with fallback)",
    "score": 62.2225,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 12.3881,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1041b2cdd9886064",
    "variant": "Devin Fusion CLI - Claude Fable 5.1 XHigh + SWE-2 Medium",
    "score": 61.6826,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Devin Fusion CLI",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 7.8971,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_fable51_api::claude-fable-5.1",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:0ed675e0b61ae3ac",
    "variant": "Claude Fable 5.1",
    "score": 80.3,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.660199,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:4748ef5e83f540ec",
    "variant": "Claude Opus 5.5 (max with fallback)",
    "score": 57.6224,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6e137e293fb02d90",
    "variant": "Claude Opus 5.5 (xhigh with fallback)",
    "score": 55.9874,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:b65a95fe350f70fe",
    "variant": "Claude Opus 5.5 (high with fallback)",
    "score": 53.5832,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6b86f0e5c649cf41",
    "variant": "Claude Opus 5.5 (medium with fallback)",
    "score": 51.2435,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:402fce0f28908149",
    "variant": "Claude Opus 5.5 (low with fallback)",
    "score": 42.3078,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:7939bf883e242fa9",
    "variant": "Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report]",
    "score": 66.4,
    "score_is_estimated": null,
    "score_is_self_reported": true,
    "agent_harness": "Claude Code",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.anthropic.com/claude-opus-5-5",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel. Vendor self-reported score, not an official leaderboard run.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a264ae9483b05c3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (max with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:23b9058c23d1ec26",
    "variant": "Artificial Analysis - Claude Opus 5.5 (xhigh with fallback)",
    "score": 59.596,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2a1794e2e04395f3",
    "variant": "Artificial Analysis - Claude Opus 5.5 (high with fallback)",
    "score": 56.5657,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:21a53e51c76d68e5",
    "variant": "Artificial Analysis - Claude Opus 5.5 (medium with fallback)",
    "score": 52.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:109f44cf79bff6a4",
    "variant": "Artificial Analysis - Claude Opus 5.5 (low with fallback)",
    "score": 31.3131,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:1eb4c01b2d86e5d0",
    "variant": "claude-opus-5.5-max",
    "score": 1818,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 1801.5,
    "score_high": 1834.5,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:b1592396c4d6d498",
    "variant": "Claude Opus 5.5 (High)",
    "score": 13.78,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 11.54,
    "score_high": 16.02,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 1.57,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_opus55_api::claude-opus-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:d3474ba216efd88d",
    "variant": "Claude Code - Opus 5.5 (max)",
    "score": 65.9886,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 13.0364,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:40ab71604b0191cd",
    "variant": "Claude Sonnet 5.5 (max with fallback)",
    "score": 55.978,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:87e4e17f2fac9de8",
    "variant": "Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 51.8523,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:07dd9777aab0951b",
    "variant": "Claude Sonnet 5.5 (high with fallback)",
    "score": 46.7357,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:328c4eadb5cbefe8",
    "variant": "Claude Sonnet 5.5 (medium with fallback)",
    "score": 40.7387,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8cbc13578cabcb6a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (max with fallback)",
    "score": 63.6364,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:e58d9ba7080efc8c",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback)",
    "score": 57.0707,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8571a16baadf9b9a",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (high with fallback)",
    "score": 43.9394,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:290fa3a81acd0ea0",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (medium with fallback)",
    "score": 29.798,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ae9b6951364c3e4",
    "variant": "Artificial Analysis - Claude Sonnet 5.5 (low with fallback)",
    "score": 20.7071,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "arena_code",
    "configuration_id": "arena_code:c72d3ba206f54fd5",
    "variant": "claude-sonnet-5.5-high",
    "score": 1709,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 1693.4,
    "score_high": 1724.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:608ea08d36d3bc63",
    "variant": "Claude Code - Sonnet 5.5 (max)",
    "score": 68.3578,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 14.1908,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:54bdbbcca087e6ff",
    "variant": "Claude Code - Sonnet 5.5 (xhigh)",
    "score": 62.8714,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 3.3334,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:197c477622a1763e",
    "variant": "Claude Code - Sonnet 5.5 (high)",
    "score": 55.0125,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 1.2355,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:5b82e4f8ad6e49f3",
    "variant": "Claude Code - Sonnet 5.5 (medium)",
    "score": 45.884,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.6188,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:1f7a78464bab7071",
    "variant": "Claude Code - Sonnet 5.5 (low)",
    "score": 42.0593,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Claude Code",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.4831,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "anthropic_sonnet55_api::claude-sonnet-5.5",
    "board": "open_design_arena",
    "configuration_id": "open_design_arena:5d69f844da6dc80d",
    "variant": "Claude Sonnet 5.5",
    "score": 86.8,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "OpenDesign",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.573814,
    "median_cost_usd_per_task": null,
    "source": "https://open-design.ai/zh/llm-arena-for-design/",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:caaac19d5e8e542f",
    "variant": "GPT-5.6 Terra (max)",
    "score": 42.0829,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:660875fc06b206b1",
    "variant": "GPT-5.6 Terra (xhigh)",
    "score": 37.9513,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:7d5413682aa8f8af",
    "variant": "GPT-5.6 Terra (high)",
    "score": 34.2377,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:32f3726769b48fd3",
    "variant": "GPT-5.6 Terra (medium)",
    "score": 30.0938,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:fcef5db6f44a9168",
    "variant": "GPT-5.6 Terra (low)",
    "score": 27.4962,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:d3febc87f28b66bc",
    "variant": "GPT-5.6 Terra (non-reasoning)",
    "score": 20.7797,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:57a5da2cde308af0",
    "variant": "Codex - GPT-5.6 Terra (max)",
    "score": 21.52,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 18.27,
    "score_high": 24.77,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:4ce13a3cd68939ad",
    "variant": "Artificial Analysis - GPT-5.6 Terra (max)",
    "score": 35.3535,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:653b68c5fe321a32",
    "variant": "Artificial Analysis - GPT-5.6 Terra (xhigh)",
    "score": 10.101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:8239d3088594c526",
    "variant": "Artificial Analysis - GPT-5.6 Terra (high)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:b68acd500c6b4161",
    "variant": "Artificial Analysis - GPT-5.6 Terra (low)",
    "score": 1.5152,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9dda7394ba62eb25",
    "variant": "Artificial Analysis - GPT-5.6 Terra (medium)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2aa44c238da36b9a",
    "variant": "Artificial Analysis - GPT-5.6 Terra (non-reasoning)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "arena_code",
    "configuration_id": "arena_code:c67b556fb4592ef2",
    "variant": "gpt-5.6-terra-xhigh (codex-harness)",
    "score": 1519,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1512.4,
    "score_high": 1525.6,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:96e32efd63046574",
    "variant": "GPT 5.6 Terra (xHigh)",
    "score": 0.83,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -0.42000000000000004,
    "score_high": 2.08,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.43,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:1e9b21c2004faec1",
    "variant": "mini-swe-agent - gpt-5-6-terra (max)",
    "score": 69.62305986696231,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 67.06612091651647,
    "score_high": 72.17999881740815,
    "mean_cost_usd_per_task": 4.945847263858093,
    "median_cost_usd_per_task": 4.114557,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:277b6c07f6ca3318",
    "variant": "mini-swe-agent - gpt-5-6-terra (xhigh)",
    "score": 60.17699115044248,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 58.052693948515355,
    "score_high": 62.30128835236961,
    "mean_cost_usd_per_task": 2.127191725663717,
    "median_cost_usd_per_task": 1.8670102499999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:31c29b4c94cf77ae",
    "variant": "mini-swe-agent - gpt-5-6-terra (high)",
    "score": 53.76106194690266,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 49.432091479689106,
    "score_high": 58.09003241411621,
    "mean_cost_usd_per_task": 1.1343762765486725,
    "median_cost_usd_per_task": 1.031709,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:900c8577e3bc443d",
    "variant": "mini-swe-agent - gpt-5-6-terra (medium)",
    "score": 35.11111111111111,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 31.729146807704478,
    "score_high": 38.49307541451774,
    "mean_cost_usd_per_task": 0.5832493688888889,
    "median_cost_usd_per_task": 0.546099,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_terra_api::gpt-5.6-terra",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:329cf994aaf09cfd",
    "variant": "mini-swe-agent - gpt-5-6-terra (low)",
    "score": 24.053452115812917,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 23.276690748868134,
    "score_high": 24.830213482757703,
    "mean_cost_usd_per_task": 0.4277452605790646,
    "median_cost_usd_per_task": 0.3989895,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:6477a68e40370653",
    "variant": "GPT-5.6 Luna (max)",
    "score": 37.3244,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:cbccf58a680025ea",
    "variant": "GPT-5.6 Luna (xhigh)",
    "score": 34.5553,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:384978b43afdd8f4",
    "variant": "GPT-5.6 Luna (high)",
    "score": 32.1196,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:60904975d230578f",
    "variant": "GPT-5.6 Luna (medium)",
    "score": 25.0359,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:5a5591e8d01f6bcc",
    "variant": "GPT-5.6 Luna (low)",
    "score": 21.0125,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_intelligence_index",
    "configuration_id": "aa_intelligence_index:ee543e6460c00da2",
    "variant": "GPT-5.6 Luna (non-reasoning)",
    "score": 15.527,
    "score_is_estimated": false,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "model_configuration_reference",
    "mapping_confidence": "medium",
    "mapping_note": "Exact served-model reference; quota-measurement effort is unverified.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "terminal_bench_4",
    "configuration_id": "terminal_bench_4:0b68373ce672d59b",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 17.27,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 14.42,
    "score_high": 20.12,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://www.tbench.ai/leaderboard",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:9c11404866580c5d",
    "variant": "Artificial Analysis - GPT-5.6 Luna (max)",
    "score": 11.6162,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:79ab9eec86d38bba",
    "variant": "Artificial Analysis - GPT-5.6 Luna (xhigh)",
    "score": 3.5354,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:f7293c3aff3fb8b9",
    "variant": "Artificial Analysis - GPT-5.6 Luna (high)",
    "score": 2.5253,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:a734c5ed959dfebb",
    "variant": "Artificial Analysis - GPT-5.6 Luna (non-reasoning)",
    "score": 1.0101,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": null,
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:1837d1adb8970232",
    "variant": "Artificial Analysis - GPT-5.6 Luna (medium)",
    "score": 0.5051,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_terminal_bench_4",
    "configuration_id": "aa_terminal_bench_4:2f7e69749a01454b",
    "variant": "Artificial Analysis - GPT-5.6 Luna (low)",
    "score": 0.0,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Artificial Analysis",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/leaderboards/models",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "arena_code",
    "configuration_id": "arena_code:fbd75732eebb198a",
    "variant": "gpt-5.6-luna-xhigh (codex-harness)",
    "score": 1518,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 1511.6,
    "score_high": 1524.4,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": null,
    "source": "https://arena.ai/leaderboard/code",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "arena_agent_mode",
    "configuration_id": "arena_agent_mode:8455f3eb58f47b3d",
    "variant": "GPT 5.6 Luna (xHigh)",
    "score": -1.09,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": null,
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": -1.79,
    "score_high": -0.3900000000000001,
    "mean_cost_usd_per_task": null,
    "median_cost_usd_per_task": 0.07,
    "source": "https://arena.ai/leaderboard/agent",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "aa_coding_agent_index",
    "configuration_id": "aa_coding_agent_index:cdca4b328af5e088",
    "variant": "Codex - GPT-5.6 Luna (max)",
    "score": 43.2247,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "Codex",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": null,
    "score_high": null,
    "mean_cost_usd_per_task": 0.438,
    "median_cost_usd_per_task": null,
    "source": "https://artificialanalysis.ai/agents/coding-agents",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7ad5b83041495e4d",
    "variant": "mini-swe-agent - gpt-5-6-luna (max)",
    "score": 67.1875,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "max",
    "service_mode": null,
    "score_low": 63.19549876432895,
    "score_high": 71.17950123567105,
    "mean_cost_usd_per_task": 3.028116810267857,
    "median_cost_usd_per_task": 2.2920917999999997,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:7a41329b22a4d1b1",
    "variant": "mini-swe-agent - gpt-5-6-luna (xhigh)",
    "score": 56.85840707964602,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "xhigh",
    "service_mode": null,
    "score_low": 54.69030532683623,
    "score_high": 59.02650883245582,
    "mean_cost_usd_per_task": 1.5356192685840708,
    "median_cost_usd_per_task": 1.2449332,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:47d55f64ef31558b",
    "variant": "mini-swe-agent - gpt-5-6-luna (high)",
    "score": 44.24778761061947,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "high",
    "service_mode": null,
    "score_low": 41.328220362702936,
    "score_high": 47.167354858536,
    "mean_cost_usd_per_task": 0.7779007499999999,
    "median_cost_usd_per_task": 0.6635542999999999,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:ec094e2327a62e03",
    "variant": "mini-swe-agent - gpt-5-6-luna (medium)",
    "score": 11.283185840707963,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "medium",
    "service_mode": null,
    "score_low": 10.452866084502313,
    "score_high": 12.113505596913615,
    "mean_cost_usd_per_task": 0.21630978982300886,
    "median_cost_usd_per_task": 0.1994702,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  },
  {
    "point_id": "openai_luna_api::gpt-5.6-luna",
    "board": "deepswe_1_1",
    "configuration_id": "deepswe_1_1:16412a120b9a4722",
    "variant": "mini-swe-agent - gpt-5-6-luna (low)",
    "score": 1.5486725663716814,
    "score_is_estimated": null,
    "score_is_self_reported": false,
    "agent_harness": "mini-swe-agent",
    "reasoning_effort": "low",
    "service_mode": null,
    "score_low": 0.7183528101660299,
    "score_high": 2.3789923225773326,
    "mean_cost_usd_per_task": 0.07240623938053097,
    "median_cost_usd_per_task": 0.0697851,
    "source": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
    "mapping_kind": "agent_configuration_reference",
    "mapping_confidence": "low",
    "mapping_note": "Exact served-model reference only; product harness and quota-measurement effort are unverified. Not a benchmark measurement of this subscription or API channel.",
    "quota_effort_matched": null
  }
]