configuration_id,board,model,variant,score_is_estimated,score_is_self_reported,agent_harness,reasoning_effort,service_mode,score,score_low,score_high,mean_cost_usd_per_task,median_cost_usd_per_task,source,checked_at,archive deepswe_1_1:aa4ad931eff45be4,deepswe_1_1,gpt-6-astra,mini-swe-agent - gpt-6-astra (xhigh),,False,mini-swe-agent,xhigh,,74.11504424778761,71.24964807371246,76.98044042186275,6.52377356460177,5.6717151,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:a4e0e06e8292b616,deepswe_1_1,gemini-3.8-flash,mini-swe-agent - gemini-3-8-flash (high),,False,mini-swe-agent,high,,73.8255033557047,72.40819014906883,75.24281656234058,2.362349413758389,2.1098912999999997,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:f029cafdaf0a4ee3,deepswe_1_1,claude-opus-5,mini-swe-agent - claude-opus-5 (max),,False,mini-swe-agent,max,,73.64864864864865,69.77633822227692,77.52095907502039,11.837583271396396,10.4281505,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e8101649c60ecba8,deepswe_1_1,gpt-6-astra,mini-swe-agent - gpt-6-astra (high),,False,mini-swe-agent,high,,73.23008849557522,69.80659243770221,76.65358455344823,5.723721956194691,4.9622669,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:b30a594ec5f66ce7,deepswe_1_1,gpt-6-astra,mini-swe-agent - gpt-6-astra (max),,False,mini-swe-agent,max,,73.23008849557522,72.39976873936956,74.06040825178087,12.369032401327434,11.036936,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:853cb17f0e600556,deepswe_1_1,claude-opus-5,mini-swe-agent - claude-opus-5 (xhigh),,False,mini-swe-agent,xhigh,,73.15436241610739,70.09338059446893,76.21534423774585,9.07220232326622,7.928816750000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e252d58fa6da2ebe,deepswe_1_1,claude-opus-5,mini-swe-agent - claude-opus-5 (high),,False,mini-swe-agent,high,,72.82850779510022,70.88307563794007,74.77393995226038,6.076084489977728,4.96882375,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:a5c5cd4b12673627,deepswe_1_1,gpt-6-astra,mini-swe-agent - gpt-6-astra (medium),,False,mini-swe-agent,medium,,72.78761061946902,70.19796153763716,75.37725970130089,4.379527705752213,3.7133415999999997,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:b7fe36ffe2e53058,deepswe_1_1,gpt-5.6-sol,mini-swe-agent - gpt-5-6-sol (max),,False,mini-swe-agent,max,,72.66666666666667,69.83684441682949,75.49648891650385,8.386436346666667,6.8414715,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:9fafa3956afdc304,deepswe_1_1,gemini-3.8-flash,mini-swe-agent - gemini-3-8-flash (medium),,False,mini-swe-agent,medium,,71.01769911504425,68.73689454216633,73.29850368792218,1.9671024789823006,1.7342966249999998,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:20ba110314745668,deepswe_1_1,gpt-5.6-sol,mini-swe-agent - gpt-5-6-sol (xhigh),,False,mini-swe-agent,xhigh,,70.73170731707317,69.91259559533886,71.55081903880748,4.703663860310422,4.117039,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:60791be82ce959e0,deepswe_1_1,claude-fable-5,mini-swe-agent - claude-fable-5 (xhigh),,False,mini-swe-agent,xhigh,,69.91150442477876,66.66658684930744,73.15642200025007,13.414521495535714,11.341082999999998,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e5e5c5b317b1f68a,deepswe_1_1,claude-fable-5,mini-swe-agent - claude-fable-5 (max),,False,mini-swe-agent,max,,69.72477064220183,65.6912963913939,73.75824489300977,21.634702092592594,19.23457225,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:1e9b21c2004faec1,deepswe_1_1,gpt-5.6-terra,mini-swe-agent - gpt-5-6-terra (max),,False,mini-swe-agent,max,,69.62305986696231,67.06612091651647,72.17999881740815,4.945847263858093,4.114557,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:b9f6b563ece4cecf,deepswe_1_1,gpt-5.6-sol,mini-swe-agent - gpt-5-6-sol (high),,False,mini-swe-agent,high,,69.40133037694012,67.9691851565629,70.83347559731736,3.4698331108647453,2.979421,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:dac434c8397694b1,deepswe_1_1,glm-5.3,mini-swe-agent - glm-5-3 (max),,False,mini-swe-agent,max,,68.95787139689578,65.93922012533709,71.97652266845449,3.9933584893126386,3.1315945999999992,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:df5db3bddc1856ee,deepswe_1_1,claude-opus-5,mini-swe-agent - claude-opus-5 (medium),,False,mini-swe-agent,medium,,68.90380313199105,67.73124446609795,70.07636179788415,3.28978764541387,2.4819885000000004,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:42fd11a99a8570ba,deepswe_1_1,claude-fable-5,mini-swe-agent - claude-fable-5 (high),,False,mini-swe-agent,high,,68.6046511627907,67.48380844536031,69.7254938802211,9.177638214788733,7.322686000000002,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:aefa4afd042df82c,deepswe_1_1,kimi-k3,mini-swe-agent - kimi-k3 (max),,False,mini-swe-agent,max,,68.51441241685144,63.97739833756913,73.05142649613376,4.654682129933482,3.6024987,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:9517554a020a7af3,deepswe_1_1,grok-4.6,mini-swe-agent - grok-4-6 (medium),,False,mini-swe-agent,medium,,67.47787610619469,65.19707153331677,69.7586806790726,3.4489837522123894,2.945834,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:7ad5b83041495e4d,deepswe_1_1,gpt-5.6-luna,mini-swe-agent - gpt-5-6-luna (max),,False,mini-swe-agent,max,,67.1875,63.19549876432895,71.17950123567105,3.028116810267857,2.2920917999999997,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:6d1742654e70dc7d,deepswe_1_1,gpt-5.5,mini-swe-agent - gpt-5-5 (xhigh),,False,mini-swe-agent,xhigh,,67.03539823008849,60.569751889179635,73.50104457099735,7.226236674778761,6.110482499999999,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:2d2b1fb9f6df06a3,deepswe_1_1,gpt-6-astra,mini-swe-agent - gpt-6-astra (low),,False,mini-swe-agent,low,,67.03539823008849,65.73453717840262,68.33625928177437,2.188762706637168,1.7209886,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:017a7f4c8bf6ada0,deepswe_1_1,grok-4.6,mini-swe-agent - grok-4-6 (xhigh),,False,mini-swe-agent,xhigh,,66.74057649667405,64.564892272269,68.9162607210791,5.497668745011087,4.63937,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e9d8d5305f3c7552,deepswe_1_1,gemini-3.7-flash,mini-swe-agent - gemini-3-7-flash (medium),,False,mini-swe-agent,medium,,65.48672566371681,62.40019338730129,68.57325794013234,2.0251351826880533,1.65422055,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:a1709ab0b129e07e,deepswe_1_1,claude-fable-5,mini-swe-agent - claude-fable-5 (medium),,False,mini-swe-agent,medium,,65.36697247706422,60.94504359782606,69.78890135630239,6.088186528935186,4.62221125,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:a62d7ab2cd07619d,deepswe_1_1,gemini-3.7-flash,mini-swe-agent - gemini-3-7-flash (high),,False,mini-swe-agent,high,,65.2654867256637,63.47762421887939,67.05334923244803,2.1762860351216813,1.9044440625,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:6c1cc54c4677acba,deepswe_1_1,grok-4.6,mini-swe-agent - grok-4-6 (high),,False,mini-swe-agent,high,,65.18847006651885,63.65486924786155,66.72207088517614,4.3848732239467845,3.693604,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:8fa6331c80979ca8,deepswe_1_1,gpt-5.5,mini-swe-agent - gpt-5-5 (high),,False,mini-swe-agent,high,,64.38053097345133,61.26368832394585,67.49737362295679,5.100437004424779,4.582879500000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:2bf6b5cf8d0df775,deepswe_1_1,glm-5.3-flash,mini-swe-agent - glm-5-3-flash (max),,False,mini-swe-agent,max,,63.39285714285714,59.0148863911635,67.77082789455078,0.48196371245535713,0.389975125,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:b317c65fa31ed642,deepswe_1_1,deepseek-v4-pro,mini-swe-agent - deepseek-v4-pro (max),,False,mini-swe-agent,max,,62.83185840707964,56.49842780985077,69.16528900430852,0.24138687892256638,0.2232531505000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:d0270ad29cebc03b,deepswe_1_1,gpt-5.6-sol,mini-swe-agent - gpt-5-6-sol (medium),,False,mini-swe-agent,medium,,61.06194690265486,59.47858925334765,62.64530455196208,1.8620318075221238,1.545414,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:277b6c07f6ca3318,deepswe_1_1,gpt-5.6-terra,mini-swe-agent - gpt-5-6-terra (xhigh),,False,mini-swe-agent,xhigh,,60.17699115044248,58.052693948515355,62.30128835236961,2.127191725663717,1.8670102499999999,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:53874601b1d3b3da,deepswe_1_1,claude-fable-5,mini-swe-agent - claude-fable-5 (low),,False,mini-swe-agent,low,,59.58429561200924,56.79029016687951,62.37830105713898,3.757873125874126,2.7559204999999998,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:03fa5cc9c1b4bc14,deepswe_1_1,claude-opus-4.8,mini-swe-agent - claude-opus-4-8 (max),,False,mini-swe-agent,max,,58.97435897435898,57.20954362692973,60.73917432178823,13.222583593240094,12.353505999999996,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:3353f4eaaecc0e42,deepswe_1_1,claude-opus-5,mini-swe-agent - claude-opus-5 (low),,False,mini-swe-agent,low,,58.12917594654788,55.79848799986361,60.45986389323216,1.6626223919821828,1.2162672499999996,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:f20515f2e81cba89,deepswe_1_1,qwen3.8-max,mini-swe-agent - qwen3-8-max (xhigh),,False,mini-swe-agent,max,,57.46102449888642,54.798231826378874,60.12381717139396,3.7290646500445437,3.132689060000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:7a41329b22a4d1b1,deepswe_1_1,gpt-5.6-luna,mini-swe-agent - gpt-5-6-luna (xhigh),,False,mini-swe-agent,xhigh,,56.85840707964602,54.69030532683623,59.02650883245582,1.5356192685840708,1.2449332,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:c181f2262d3e9d70,deepswe_1_1,muse-spark-1.2,mini-swe-agent - muse-spark-1-2 (xhigh),,False,mini-swe-agent,xhigh,,54.86725663716814,52.74295943524101,56.99155383909527,3.6955048180309733,2.6840506,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:9ba29daf22e9a1ae,deepswe_1_1,claude-opus-4.8,mini-swe-agent - claude-opus-4-8 (xhigh),,False,mini-swe-agent,xhigh,,54.36241610738255,50.64898547928808,58.07584673547702,8.006355704138702,7.049357750000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:f4c657e2ffa66931,deepswe_1_1,gpt-5.5,mini-swe-agent - gpt-5-5 (medium),,False,mini-swe-agent,medium,,53.98230088495575,51.42921338966476,56.53538838024673,2.749342734513274,2.436942,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:17f1ccadd79e3f73,deepswe_1_1,claude-sonnet-5,mini-swe-agent - claude-sonnet-5 (max),,False,mini-swe-agent,max,,53.84615384615385,49.60923737597946,58.08307031632823,26.399858950791852,23.277376725000003,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:c3c0d085a762f3d1,deepswe_1_1,gemini-3.7-flash,mini-swe-agent - gemini-3-7-flash (low),,False,mini-swe-agent,low,,53.76106194690266,51.171412865070785,56.35071102873452,1.8322645629424779,1.3913454375,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:31c29b4c94cf77ae,deepswe_1_1,gpt-5.6-terra,mini-swe-agent - gpt-5-6-terra (high),,False,mini-swe-agent,high,,53.76106194690266,49.432091479689106,58.09003241411621,1.1343762765486725,1.031709,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:70b6e868fcb9cd80,deepswe_1_1,grok-4.5,mini-swe-agent - grok-4-5 (high),,False,mini-swe-agent,high,,53.76106194690266,51.48025737402474,56.04186651978057,2.4157481725663716,2.02311,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:c0668bd778ebe124,deepswe_1_1,deepseek-v4-flash,mini-swe-agent - deepseek-v4-flash (max),,False,mini-swe-agent,max,,53.31858407079646,49.751633855764034,56.88553428582889,0.10023560370265487,0.09124898719999996,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e18ab480d9cf17e0,deepswe_1_1,muse-spark-1.1,mini-swe-agent - muse-spark-1-1 (xhigh),,False,mini-swe-agent,xhigh,,53.31858407079646,50.28324161686275,56.35392652473017,2.361142644469026,1.7171158,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:2b59cc2e16364e15,deepswe_1_1,claude-opus-4.8,mini-swe-agent - claude-opus-4-8 (high),,False,mini-swe-agent,high,,51.76991150442478,47.20830235866894,56.33152065018062,4.281940017699115,3.6635345,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:148350e563933fb6,deepswe_1_1,gpt-5.4,mini-swe-agent - gpt-5-4 (xhigh),,False,mini-swe-agent,xhigh,,51.76991150442478,50.2678065476865,53.27201646116306,5.6524577245575225,4.3528565,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:6a089e055d07f388,deepswe_1_1,claude-sonnet-5,mini-swe-agent - claude-sonnet-5 (xhigh),,False,mini-swe-agent,xhigh,,49.667405764966745,46.21285677328888,53.121954756644605,11.890634540022173,9.965361750000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:7d16a6959bd957f6,deepswe_1_1,claude-opus-4.8,mini-swe-agent - claude-opus-4-8 (medium),,False,mini-swe-agent,medium,,48.67256637168141,46.43336050994396,50.91177223341886,3.4438571028761062,2.84043425,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e833a890e9fc6ef0,deepswe_1_1,claude-sonnet-5,mini-swe-agent - claude-sonnet-5 (high),,False,mini-swe-agent,high,,48.23008849557522,43.72377362536038,52.73640336579006,7.425560161197339,5.833649100000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:e1743e5569cb8648,deepswe_1_1,gemini-3.6-flash,mini-swe-agent - gemini-3-6-flash (high),,False,mini-swe-agent,high,,46.68141592920354,42.97656202995626,50.386269828450814,4.419013277333334,3.444695325000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:eed6875ca51165fd,deepswe_1_1,gpt-5.6-sol,mini-swe-agent - gpt-5-6-sol (low),,False,mini-swe-agent,low,,45.35398230088495,42.96578762942603,47.74217697234388,1.0742664646017699,0.944557,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:47d55f64ef31558b,deepswe_1_1,gpt-5.6-luna,mini-swe-agent - gpt-5-6-luna (high),,False,mini-swe-agent,high,,44.24778761061947,41.328220362702936,47.167354858536,0.7779007499999999,0.6635542999999999,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:3c0de09601f2c8a8,deepswe_1_1,glm-5.2,mini-swe-agent - glm-5-2 (max),,False,mini-swe-agent,max,,43.77777777777778,42.05214815719697,45.50340739835859,3.9199075743111114,3.4637479200000003,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:baca3e04439efe09,deepswe_1_1,grok-4.6,mini-swe-agent - grok-4-6 (low),,False,mini-swe-agent,low,,41.648106904231625,39.32945513980172,43.96675866866153,1.0423604231625836,0.742614,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:39deebcf76251bec,deepswe_1_1,claude-opus-4.8,mini-swe-agent - claude-opus-4-8 (low),,False,mini-swe-agent,low,,40.79822616407982,39.334641405510666,42.261810922648976,2.293369216740577,1.8240152500000004,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:3cee9c2890b172bc,deepswe_1_1,claude-sonnet-5,mini-swe-agent - claude-sonnet-5 (medium),,False,mini-swe-agent,medium,,39.77777777777778,36.65020157144805,42.90535398410751,4.079036229,3.3573110999999995,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:71a3c9c8333b9bfd,deepswe_1_1,glm-5.2,mini-swe-agent - glm-5-2 (high),,False,mini-swe-agent,high,,36.283185840707965,31.533112892786306,41.033258788629624,2.8355164725663715,2.25012998,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:c9919ba8b7aa7d29,deepswe_1_1,gemini-3.5-flash,mini-swe-agent - gemini-3-5-flash (high),,False,mini-swe-agent,high,,36.06194690265487,32.095643892134426,40.02824991317531,3.4467114588691796,2.8624087500000015,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:900c8577e3bc443d,deepswe_1_1,gpt-5.6-terra,mini-swe-agent - gpt-5-6-terra (medium),,False,mini-swe-agent,medium,,35.11111111111111,31.729146807704478,38.49307541451774,0.5832493688888889,0.546099,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:c25e237262636381,deepswe_1_1,kimi-k2.7-code,mini-swe-agent - kimi-k2-7-code (None),,False,mini-swe-agent,none,,30.53097345132743,30.030271799081337,31.031675103573527,2.815536243274336,2.1955079100000003,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:4b4fac04da320c00,deepswe_1_1,claude-sonnet-5,mini-swe-agent - claude-sonnet-5 (low),,False,mini-swe-agent,low,,30.51224944320713,29.386231901764383,31.638266984649878,2.1865550832962137,1.6764955500000003,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:ad99a40bfe39fad2,deepswe_1_1,claude-sonnet-4.6,mini-swe-agent - claude-sonnet-4-6 (high),,False,mini-swe-agent,high,,29.933481152993345,25.84133988380421,34.02562242218249,5.5223517987804875,4.867440150000001,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:94c61fbd52e4cefa,deepswe_1_1,gpt-5.5,mini-swe-agent - gpt-5-5 (low),,False,mini-swe-agent,low,,26.991150442477874,24.696647220470695,29.285653664485057,1.2002025442477877,1.108106,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:329cf994aaf09cfd,deepswe_1_1,gpt-5.6-terra,mini-swe-agent - gpt-5-6-terra (low),,False,mini-swe-agent,low,,24.053452115812917,23.276690748868134,24.830213482757703,0.4277452605790646,0.3989895,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:d8f3d12f6e586e1d,deepswe_1_1,gemini-3.1-pro-preview,mini-swe-agent - gemini-3-1-pro-preview (high),,False,mini-swe-agent,high,,11.725663716814159,10.244568255705316,13.206759177923006,2.1434045568888886,1.7235064000000002,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:ec094e2327a62e03,deepswe_1_1,gpt-5.6-luna,mini-swe-agent - gpt-5-6-luna (medium),,False,mini-swe-agent,medium,,11.283185840707963,10.452866084502313,12.113505596913615,0.21630978982300886,0.1994702,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:16412a120b9a4722,deepswe_1_1,gpt-5.6-luna,mini-swe-agent - gpt-5-6-luna (low),,False,mini-swe-agent,low,,1.5486725663716814,0.7183528101660299,2.3789923225773326,0.07240623938053097,0.0697851,https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json,2026-09-12,scores-deepswe-1.1-2026-09-12.json deepswe_1_1:3d9b43ea1f40d6be,deepswe_1_1,deepseek-v4.1-flash,mini-SWE - DeepSeek V4.1 Flash (max) [vendor self-report],,True,mini-SWE,max,,74.2,,,,,https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash,2026-09-12,scores-deepswe-selfreport-2026-09-12.json deepswe_1_1:9454d8de1c52f2fc,deepswe_1_1,mimo-v2.6-pro,mini-swe-agent - mimo-v2-6-pro [vendor self-report],,True,mini-swe-agent,,,71.9,,,,,https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL,2026-09-22,scores-deepswe-mimo-v26-grok47-selfreport-2026-09-22.json deepswe_1_1:c2b10fcdefbd0221,deepswe_1_1,mimo-v2.6-flash,mini-swe-agent - mimo-v2-6-flash [vendor self-report],,True,mini-swe-agent,,,67.9,,,,,https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL,2026-09-22,scores-deepswe-mimo-v26-grok47-selfreport-2026-09-22.json deepswe_1_1:8fa241178a2088a2,deepswe_1_1,mimo-v2.5-pro,mini-swe-agent - mimo-v2-5-pro [vendor self-report],,True,mini-swe-agent,,,19.0,,,,,https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL,2026-09-22,scores-deepswe-mimo-v26-grok47-selfreport-2026-09-22.json deepswe_1_1:1d433900eaa0bee0,deepswe_1_1,grok-4.7,mini-swe-agent - grok-4-7 (high) [vendor self-report],,True,mini-swe-agent,high,,71.0,,,,,https://x.ai/news/grok-4-7,2026-09-22,scores-deepswe-mimo-v26-grok47-selfreport-2026-09-22.json aa_intelligence_index:4748ef5e83f540ec,aa_intelligence_index,claude-opus-5.5,Claude Opus 5.5 (max with fallback),False,False,,max,,57.6224,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:6e137e293fb02d90,aa_intelligence_index,claude-opus-5.5,Claude Opus 5.5 (xhigh with fallback),False,False,,xhigh,,55.9874,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:40ab71604b0191cd,aa_intelligence_index,claude-sonnet-5.5,Claude Sonnet 5.5 (max with fallback),False,False,,max,,55.978,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b65a95fe350f70fe,aa_intelligence_index,claude-opus-5.5,Claude Opus 5.5 (high with fallback),False,False,,high,,53.5832,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:71823637d973a0fc,aa_intelligence_index,claude-fable-5.1,Claude Fable 5.1 (max with fallback),False,False,,max,,53.3549,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:3f66aafbb8812925,aa_intelligence_index,claude-fable-5.1,Claude Fable 5.1 (xhigh with fallback),False,False,,xhigh,,53.2033,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:9b1da82a91856d8d,aa_intelligence_index,gpt-6-astra,GPT-6 Astra (max),False,False,,max,,52.6737,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:7070b585da6e3a29,aa_intelligence_index,gpt-6-astra,GPT-6 Astra (xhigh),False,False,,xhigh,,52.3863,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:87e4e17f2fac9de8,aa_intelligence_index,claude-sonnet-5.5,Claude Sonnet 5.5 (xhigh with fallback),False,False,,xhigh,,51.8523,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b6ad871a45a4a5df,aa_intelligence_index,gpt-6.1-sol,GPT-6.1 Sol (max),False,False,,max,,51.8333,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:6b86f0e5c649cf41,aa_intelligence_index,claude-opus-5.5,Claude Opus 5.5 (medium with fallback),False,False,,medium,,51.2435,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:74265ef58fb6e45b,aa_intelligence_index,claude-fable-5.1,Claude Fable 5.1 (high with fallback),False,False,,high,,51.1516,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:4a8f2c60cc909b11,aa_intelligence_index,gpt-6.1-sol,GPT-6.1 Sol (xhigh),False,False,,xhigh,,51.0378,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:7c09034755a992fc,aa_intelligence_index,gpt-6-astra,GPT-6 Astra (high),False,False,,high,,50.9191,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:68425237e9876779,aa_intelligence_index,claude-opus-5,Claude Opus 5 (max),False,False,,max,,50.7771,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:aea0241d837a4380,aa_intelligence_index,gpt-6.1-sol,GPT-6.1 Sol (high),False,False,,high,,50.2378,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:3a154cb4e9c99189,aa_intelligence_index,claude-opus-5,Claude Opus 5 (xhigh),False,False,,xhigh,,49.6774,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:9b5f20f46c907550,aa_intelligence_index,claude-fable-5,Claude Fable 5 (with fallback),False,False,,,,49.6258,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:3cf95b4f1be42e0f,aa_intelligence_index,gpt-6-astra,GPT-6 Astra (medium),False,False,,medium,,49.5704,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:9a927f4404e32355,aa_intelligence_index,claude-fable-5.1,Claude Fable 5.1 (medium with fallback),False,False,,medium,,48.9206,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:295f5f7bdfa8d248,aa_intelligence_index,claude-opus-5,Claude Opus 5 (high),False,False,,high,,48.1219,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:a8c28362dff3aa31,aa_intelligence_index,muse-spark-1.3,Muse Spark 1.3 (max),False,False,,max,,48.0923,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e4a9f446e946fc59,aa_intelligence_index,gpt-6.1-sol,GPT-6.1 Sol (medium),False,False,,medium,,47.7833,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:ca545106241767d7,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (max),False,False,,max,,47.5276,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c95dc5141f32b497,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (max),False,False,,max,,46.9727,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2ceeec877967a38a,aa_intelligence_index,claude-fable-5.1,Claude Fable 5.1 (low with fallback),False,False,,low,,46.8163,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:07dd9777aab0951b,aa_intelligence_index,claude-sonnet-5.5,Claude Sonnet 5.5 (high with fallback),False,False,,high,,46.7357,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:d11843ec849da6d9,aa_intelligence_index,grok-4.7,Grok 4.7 (xhigh),False,False,,xhigh,,46.4466,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:0c727f941b7eae61,aa_intelligence_index,grok-4.7,Grok 4.7 (high),False,False,,high,,46.3322,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:83bd852b96aedbce,aa_intelligence_index,mimo-v2.6-pro,MiMo-V2.6-Pro,False,False,,,,46.3242,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:6858c62f40a2b8a3,aa_intelligence_index,gpt-6-astra,GPT-6 Astra (low),False,False,,low,,45.7819,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c9c2272b5b7ddbdf,aa_intelligence_index,qwen3.8-max-0902,Qwen3.8 Max (0902),False,False,,max,,45.4152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:eaee770ce12a30df,aa_intelligence_index,muse-spark-1.3,Muse Spark 1.3 (xhigh),False,False,,xhigh,,45.0733,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:bacfec5f5f91d13c,aa_intelligence_index,claude-opus-5,Claude Opus 5 (medium),False,False,,medium,,44.8253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:21922ac966701739,aa_intelligence_index,glm-5.3,GLM-5.3 (max),False,False,,max,,44.7774,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b56103ded435971f,aa_intelligence_index,grok-4.6,Grok 4.6 (high),False,False,,high,,44.3113,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:13ecd3c1725d233e,aa_intelligence_index,grok-4.6,Grok 4.6 (xhigh),False,False,,xhigh,,44.1998,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:ec3291a5ccf1d360,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (xhigh),False,False,,xhigh,,44.101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:467034ea7730fe43,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (xhigh),False,False,,xhigh,,44.0089,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:fb0405a168316f85,aa_intelligence_index,step-5-preview,Step 5 Preview,False,False,,,,43.7343,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:13115cf53ac21275,aa_intelligence_index,kimi-k3,Kimi K3 (max),False,False,,max,,43.5938,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2df81011d518b272,aa_intelligence_index,grok-4.6,Grok 4.6 (medium),False,False,,medium,,42.8363,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b88d90b9ef2bcc13,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (high),False,False,,high,,42.8216,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:5b0f75c30f0ab19b,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (high),False,False,,high,,42.3461,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:402fce0f28908149,aa_intelligence_index,claude-opus-5.5,Claude Opus 5.5 (low with fallback),False,False,,low,,42.3078,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:f49734a44b6bfe83,aa_intelligence_index,gpt-6.1-sol,GPT-6.1 Sol (low),False,False,,low,,42.0836,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:caaac19d5e8e542f,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (max),False,False,,max,,42.0829,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:066a860a43b7204e,aa_intelligence_index,glm-5.3-flash,GLM-5.3-Flash,False,False,,,,41.8075,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:8ba60e513dcc3861,aa_intelligence_index,claude-opus-4.8,Claude Opus 4.8 (max),False,False,,max,,41.7899,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:a795ed51d673418d,aa_intelligence_index,gemini-3.8-flash,Gemini 3.8 Flash (high),False,False,,high,,40.9262,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:328c4eadb5cbefe8,aa_intelligence_index,claude-sonnet-5.5,Claude Sonnet 5.5 (medium with fallback),False,False,,medium,,40.7387,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:8919405f90e7565f,aa_intelligence_index,qwen3.8-max,Qwen3.8 Max,False,False,,max,,40.1529,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:5dea08c56cadf0a5,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (medium),False,False,,medium,,39.7821,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:8f226080bd0bde9a,aa_intelligence_index,gemini-3.8-flash,Gemini 3.8 Flash (medium),False,False,,medium,,39.774,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:59269287bc1e95d8,aa_intelligence_index,gemini-3.7-flash,Gemini 3.7 Flash (medium) [AA estimate],True,False,,medium,,39.6178,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:9666106dbc0fffc1,aa_intelligence_index,muse-spark-1.2,Muse Spark 1.2 (xhigh),False,False,,xhigh,,39.5759,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:8076c0cba16368e2,aa_intelligence_index,deepseek-v4.1-flash,DeepSeek V4.1 Flash (max),False,False,,max,,39.4562,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e42133cf9100a842,aa_intelligence_index,claude-opus-5,Claude Opus 5 (low),False,False,,low,,39.3543,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:64efdbd82ca66394,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (medium),False,False,,medium,,39.2364,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:aeabf6017dd74bc8,aa_intelligence_index,gemini-3.7-flash,Gemini 3.7 Flash (high),False,False,,high,,39.0595,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:829ff4209a0293bc,aa_intelligence_index,grok-4.5,Grok 4.5 (high),False,False,,high,,38.8121,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c4bfcb80a46cebef,aa_intelligence_index,gpt-5.5,GPT-5.5 (xhigh),False,False,,xhigh,,38.3556,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:00e5e17098f2a9cc,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (max),False,False,,max,,38.1639,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:660875fc06b206b1,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (xhigh),False,False,,xhigh,,37.9513,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2446e4ad7216a14c,aa_intelligence_index,mimo-v2.6-flash,MiMo-V2.6-Flash,False,False,,,,37.8844,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:6477a68e40370653,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (max),False,False,,max,,37.3244,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e41e4b6709da24d4,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (max),False,False,,max,,37.256,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:6fd00cd9ccb51b99,aa_intelligence_index,gpt-5.5,GPT-5.5 (high),False,False,,high,,36.9794,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:cc014f66e9d183e0,aa_intelligence_index,gemini-3.7-flash,Gemini 3.7 Flash (low) [AA estimate],True,False,,low,,36.9459,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e551b2b658c831ff,aa_intelligence_index,deepseek-v4-pro,DeepSeek V4 Pro 0813 (max),False,False,,max,,35.9968,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2e9f902e3fc120db,aa_intelligence_index,grok-4.6,Grok 4.6 (low),False,False,,low,,35.1247,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2ab3fed6fb264856,aa_intelligence_index,deepseek-v4-flash-vision-exp,DeepSeek V4 Flash Vision (max),False,False,,max,,34.8391,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:cbccf58a680025ea,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (xhigh),False,False,,xhigh,,34.5553,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:26fc619ae9c44efb,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (xhigh),False,False,,xhigh,,34.3842,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b6a092361e695dd6,aa_intelligence_index,deepseek-v4-flash,DeepSeek V4 Flash 0731 (max),False,False,,max,,34.3305,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:237ff152b6aa847d,aa_intelligence_index,glm-5.3,GLM-5.3 (low),False,False,,low,,34.299,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:7d5413682aa8f8af,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (high),False,False,,high,,34.2377,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c190b81e19d238cc,aa_intelligence_index,gemini-3.6-flash,Gemini 3.6 Flash (high),False,False,,high,,33.9786,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:db3deb60f0a6f0ac,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (low),False,False,,low,,33.9009,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:711bafc42ade2516,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (xhigh),False,False,,xhigh,,33.8846,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:22a192a88d4be69a,aa_intelligence_index,gpt-5.5,GPT-5.5 (medium),False,False,,medium,,33.8044,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:4b9229f7a5210ab7,aa_intelligence_index,glm-5.2,GLM-5.2 (max),False,False,,max,,33.7055,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:4555232c8e387389,aa_intelligence_index,qwen3.8-27b,Qwen3.8 27B (xhigh),False,False,,xhigh,,33.6963,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:d1b16dee33968223,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (low),False,False,,low,,33.4731,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e0b41460917d3eff,aa_intelligence_index,gemini-3.8-flash,Gemini 3.8 Flash (low),False,False,,low,,33.4548,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:927f29d66e09bcc0,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (high),False,False,,high,,32.1482,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:384978b43afdd8f4,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (high),False,False,,high,,32.1196,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c089bab844997713,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (high),False,False,,high,,31.6623,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c3e9b37ac894d3d3,aa_intelligence_index,gpt-5.5,GPT-5.5 (low) [AA estimate],True,False,,low,,30.7095,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:99ded62ad6efb9a5,aa_intelligence_index,deepseek-v4-pro,DeepSeek V4 Pro (max),False,False,,max,,30.4497,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:1635385ef12eb561,aa_intelligence_index,deepseek-v4-pro,DeepSeek V4 Pro (high) [AA estimate],True,False,,high,,30.1055,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:32f3726769b48fd3,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (medium),False,False,,medium,,30.0938,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:50501b171b1855d0,aa_intelligence_index,kimi-k3,Kimi K3 (low),False,False,,low,,30.0667,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:cc1fed45bce203af,aa_intelligence_index,gemini-3.1-pro,Gemini 3.1 Pro Preview,False,False,,,,29.7186,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:51051c5b6fc81a75,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (medium),False,False,,medium,,29.462,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b3246639fa93a057,aa_intelligence_index,qwen3.7-max,Qwen3.7 Max,False,False,,max,,29.4572,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:179c62d659734cb1,aa_intelligence_index,minimax-m3,MiniMax-M3,False,False,,,,29.2203,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:3a58445ae77253e4,aa_intelligence_index,qwen3.6-max-preview,Qwen3.6 Max Preview [AA estimate],True,False,,max,,28.3749,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:15f1554828f5b0dc,aa_intelligence_index,gpt-5.6-sol,GPT-5.6 Sol (non-reasoning) [AA estimate],True,False,,,,28.328,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:49ed8f07e3584753,aa_intelligence_index,gpt-6-sol,GPT-6 Sol (non-reasoning),False,False,,,,28.0922,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2b12f7c3563de350,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (medium),False,False,,medium,,28.0531,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b5ff5400e6b8641a,aa_intelligence_index,glm-5,GLM-5 [AA estimate],True,False,,,,27.9112,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:386e5826aefad337,aa_intelligence_index,qwen3.8-27b,Qwen3.8 27B (medium),False,False,,medium,,27.5508,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:fcef5db6f44a9168,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (low),False,False,,low,,27.4962,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:238aba7e1b811926,aa_intelligence_index,qwen3.6-plus,Qwen3.6 Plus [AA estimate],True,False,,,,27.0099,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:97c970284455bffa,aa_intelligence_index,kimi-k2.6,Kimi K2.6,False,False,,,,26.9792,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:d136741f62069cb1,aa_intelligence_index,qwen3.8-27b,Qwen3.8 27B (low),False,False,,low,,26.2048,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:f45138a64ed521bd,aa_intelligence_index,glm-5.1,GLM-5.1,False,False,,,,26.0586,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:c0536a98a4f2e51d,aa_intelligence_index,mimo-v2.5-pro,MiMo-V2.5-Pro,False,False,,,,25.9869,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b0c9eb24f253523d,aa_intelligence_index,kimi-k2.7-code,Kimi K2.7 Code,False,False,,,,25.8121,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2ecad05994d7b1af,aa_intelligence_index,inkling-small,Inkling Small,False,False,,,,25.6583,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:131d42e954c0324c,aa_intelligence_index,hy3,Hy3,False,False,,,,25.2973,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:4f0191d02e894561,aa_intelligence_index,mimo-v2.5,MiMo-V2.5 [AA estimate],True,False,,,,25.1743,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:2e94df38c6b223ca,aa_intelligence_index,qwen3.7-plus,Qwen3.7 Plus,False,False,,,,25.1622,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:60904975d230578f,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (medium),False,False,,medium,,25.0359,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:ae97bbe112769bcd,aa_intelligence_index,inkling,Inkling (xhigh),False,False,,xhigh,,24.9848,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:d81376edf86feffa,aa_intelligence_index,deepseek-v4.1-flash,DeepSeek V4.1 Flash (non-reasoning),False,False,,,,24.6734,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:7cb5e674535a254b,aa_intelligence_index,deepseek-v4-flash,DeepSeek V4 Flash (high),False,False,,high,,24.384,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:b99819b727eb71df,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (low),False,False,,low,,24.2638,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:18011484156b18b6,aa_intelligence_index,glm-5.1,GLM-5.1 (non-reasoning) [AA estimate],True,False,,,,24.2412,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:db4df116f5cc1c83,aa_intelligence_index,deepseek-v4-flash,DeepSeek V4 Flash (max),False,False,,max,,24.1673,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:be58b1c3ec11fb7d,aa_intelligence_index,kimi-k2.6,Kimi K2.6 (non-reasoning) [AA estimate],True,False,,,,23.5696,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:589e83427c9b8ab7,aa_intelligence_index,kimi-k2.5,Kimi K2.5 [AA estimate],True,False,,,,23.4585,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e35c69aedd168116,aa_intelligence_index,claude-sonnet-5,Claude Sonnet 5 (non-reasoning) [AA estimate],True,False,,,,23.2,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e75792c6ebb8bb80,aa_intelligence_index,gpt-5.5,GPT-5.5 (non-reasoning) [AA estimate],True,False,,,,23.1674,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:5cd72513bff7d4b7,aa_intelligence_index,nemotron-3-ultra,Nemotron 3 Ultra,False,False,,,,22.9279,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:ae390fdc5fe89d6c,aa_intelligence_index,minimax-m2.5,MiniMax-M2.5 [AA estimate],True,False,,,,22.7966,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:58eba7a1df2c56c5,aa_intelligence_index,minimax-m2.7,MiniMax-M2.7,False,False,,,,22.7578,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:bf6c2c604a56c9d0,aa_intelligence_index,glm-5.2,GLM-5.2 (non-reasoning) [AA estimate],True,False,,,,22.4323,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:81bcbed3fd5a66b9,aa_intelligence_index,glm-5,GLM-5 (non-reasoning) [AA estimate],True,False,,,,21.7826,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:5a5591e8d01f6bcc,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (low),False,False,,low,,21.0125,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:9e4a1080bc5cdeda,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (low),False,False,,low,,20.9225,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e15aa3daea8ed086,aa_intelligence_index,deepseek-v4-pro,DeepSeek V4 Pro (non-reasoning) [AA estimate],True,False,,,,20.8345,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:d3febc87f28b66bc,aa_intelligence_index,gpt-5.6-terra,GPT-5.6 Terra (non-reasoning),False,False,,,,20.7797,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:f323daf280bfff22,aa_intelligence_index,deepseek-v4-pro,DeepSeek V4 Pro 0813 (non-reasoning),False,False,,,,20.3605,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:7bed7be52e30496d,aa_intelligence_index,qwen3.8-27b,Qwen3.8 27B (non-reasoning),False,False,,,,20.1502,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:e8828ee245d130af,aa_intelligence_index,step-3.7-flash,Step 3.7 Flash [AA estimate],True,False,,,,19.4813,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:1afe01378404f2e7,aa_intelligence_index,kimi-k2.5,Kimi K2.5 (non-reasoning) [AA estimate],True,False,,,,19.4343,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:73481783e67e2f5b,aa_intelligence_index,longcat-2.0,LongCat 2.0,False,False,,,,19.1123,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:610f4083dbb622ce,aa_intelligence_index,deepseek-v4-flash,DeepSeek V4 Flash (non-reasoning) [AA estimate],True,False,,,,18.8769,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:95331afc94452f27,aa_intelligence_index,mimo-v2.5-pro,MiMo-V2.5-Pro (non-reasoning) [AA estimate],True,False,,,,18.29,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:be701ec71aacde7a,aa_intelligence_index,gpt-6-luna,GPT-6 Luna (non-reasoning),False,False,,,,18.2617,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:f4ecc0cb880e6a93,aa_intelligence_index,step-3.5-flash,Step 3.5 Flash 2603 [AA estimate],True,False,,,,16.9641,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:19396846e36b1f6e,aa_intelligence_index,step-3.5-flash,Step 3.5 Flash [AA estimate],True,False,,,,16.6169,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:ee543e6460c00da2,aa_intelligence_index,gpt-5.6-luna,GPT-5.6 Luna (non-reasoning),False,False,,,,15.527,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_intelligence_index:479a072abc28cf2a,aa_intelligence_index,mistral-medium-3.5,Mistral Medium 3.5,False,False,,medium,,14.1889,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8cbc13578cabcb6a,aa_terminal_bench_4,claude-sonnet-5.5,Artificial Analysis - Claude Sonnet 5.5 (max with fallback),,False,Artificial Analysis,max,,63.6364,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:700453154be041cb,aa_terminal_bench_4,gpt-6-astra,Artificial Analysis - GPT-6 Astra (xhigh),,False,Artificial Analysis,xhigh,,59.596,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2a264ae9483b05c3,aa_terminal_bench_4,claude-opus-5.5,Artificial Analysis - Claude Opus 5.5 (max with fallback),,False,Artificial Analysis,max,,59.596,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:23b9058c23d1ec26,aa_terminal_bench_4,claude-opus-5.5,Artificial Analysis - Claude Opus 5.5 (xhigh with fallback),,False,Artificial Analysis,xhigh,,59.596,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:e44812025afd889c,aa_terminal_bench_4,gpt-6-astra,Artificial Analysis - GPT-6 Astra (max),,False,Artificial Analysis,max,,59.0909,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:e58d9ba7080efc8c,aa_terminal_bench_4,claude-sonnet-5.5,Artificial Analysis - Claude Sonnet 5.5 (xhigh with fallback),,False,Artificial Analysis,xhigh,,57.0707,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2a1794e2e04395f3,aa_terminal_bench_4,claude-opus-5.5,Artificial Analysis - Claude Opus 5.5 (high with fallback),,False,Artificial Analysis,high,,56.5657,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:f935d95ba064b29b,aa_terminal_bench_4,gpt-6.1-sol,Artificial Analysis - GPT-6.1 Sol (max),,False,Artificial Analysis,max,,56.0606,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:41e12ce515ec9121,aa_terminal_bench_4,claude-fable-5.1,Artificial Analysis - Claude Fable 5.1 (xhigh with fallback),,False,Artificial Analysis,xhigh,,55.0505,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:94af356c207fc48e,aa_terminal_bench_4,gpt-6.1-sol,Artificial Analysis - GPT-6.1 Sol (xhigh),,False,Artificial Analysis,xhigh,,54.0404,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:12ee7971061ca0e0,aa_terminal_bench_4,gpt-6-astra,Artificial Analysis - GPT-6 Astra (high),,False,Artificial Analysis,high,,54.0404,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:21a53e51c76d68e5,aa_terminal_bench_4,claude-opus-5.5,Artificial Analysis - Claude Opus 5.5 (medium with fallback),,False,Artificial Analysis,medium,,52.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:1512d68b0eb6bc1b,aa_terminal_bench_4,claude-fable-5.1,Artificial Analysis - Claude Fable 5.1 (max with fallback),,False,Artificial Analysis,max,,52.0202,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:e606b01ceda846f9,aa_terminal_bench_4,claude-fable-5.1,Artificial Analysis - Claude Fable 5.1 (high with fallback),,False,Artificial Analysis,high,,52.0202,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c77efb6f723a47b3,aa_terminal_bench_4,gpt-6.1-sol,Artificial Analysis - GPT-6.1 Sol (high),,False,Artificial Analysis,high,,51.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0634c4abcbad70cc,aa_terminal_bench_4,gpt-6-astra,Artificial Analysis - GPT-6 Astra (medium),,False,Artificial Analysis,medium,,49.4949,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0ed48e92962897a4,aa_terminal_bench_4,claude-opus-5,Artificial Analysis - Claude Opus 5 (max),,False,Artificial Analysis,max,,48.9899,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8f793b0822f5faf4,aa_terminal_bench_4,gpt-6.1-sol,Artificial Analysis - GPT-6.1 Sol (medium),,False,Artificial Analysis,medium,,47.9798,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0838ca37e5fa42da,aa_terminal_bench_4,claude-opus-5,Artificial Analysis - Claude Opus 5 (xhigh),,False,Artificial Analysis,xhigh,,46.4646,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8e10956f03aaa14d,aa_terminal_bench_4,claude-opus-5,Artificial Analysis - Claude Opus 5 (high),,False,Artificial Analysis,high,,45.9596,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:93ccfc6e6c1f4910,aa_terminal_bench_4,claude-fable-5.1,Artificial Analysis - Claude Fable 5.1 (medium with fallback),,False,Artificial Analysis,medium,,44.9495,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8571a16baadf9b9a,aa_terminal_bench_4,claude-sonnet-5.5,Artificial Analysis - Claude Sonnet 5.5 (high with fallback),,False,Artificial Analysis,high,,43.9394,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c54c846fa56e7fb9,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (max),,False,Artificial Analysis,max,,43.9394,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:6fd65552e1fc1e0a,aa_terminal_bench_4,claude-fable-5,Artificial Analysis - Claude Fable 5 (with fallback),,False,Artificial Analysis,,,42.4242,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4785a3610e775817,aa_terminal_bench_4,gpt-6-astra,Artificial Analysis - GPT-6 Astra (low),,False,Artificial Analysis,low,,41.9192,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:496fda38cce0cdb6,aa_terminal_bench_4,glm-5.3,Artificial Analysis - GLM-5.3 (max),,False,Artificial Analysis,max,,41.9192,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:5e01b08628a88aac,aa_terminal_bench_4,claude-fable-5.1,Artificial Analysis - Claude Fable 5.1 (low with fallback),,False,Artificial Analysis,low,,40.404,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:7ac4c013fed0b565,aa_terminal_bench_4,gpt-5.6-sol,Artificial Analysis - GPT-5.6 Sol (max),,False,Artificial Analysis,max,,39.899,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:696204be45eb44af,aa_terminal_bench_4,qwen3.8-max-0902,Artificial Analysis - Qwen3.8 Max (0902),,False,Artificial Analysis,max,,38.8889,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4ce13a3cd68939ad,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (max),,False,Artificial Analysis,max,,35.3535,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:b5691a8df0db5041,aa_terminal_bench_4,mimo-v2.6-pro,Artificial Analysis - MiMo-V2.6-Pro,,False,Artificial Analysis,,,34.8485,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:69eafd0d76477763,aa_terminal_bench_4,glm-5.3,Artificial Analysis - GLM-5.3 (low),,False,Artificial Analysis,low,,34.8485,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:314fe657e048e298,aa_terminal_bench_4,claude-opus-5,Artificial Analysis - Claude Opus 5 (medium),,False,Artificial Analysis,medium,,34.3434,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:e7fa06d82cc14898,aa_terminal_bench_4,step-5-preview,Artificial Analysis - Step 5 Preview,,False,Artificial Analysis,,,33.3333,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:3ceb10cebdd638c2,aa_terminal_bench_4,muse-spark-1.3,Artificial Analysis - Muse Spark 1.3 (max),,False,Artificial Analysis,max,,33.3333,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:458e21cad837a439,aa_terminal_bench_4,glm-5.3-flash,Artificial Analysis - GLM-5.3-Flash,,False,Artificial Analysis,,,32.8283,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:109f44cf79bff6a4,aa_terminal_bench_4,claude-opus-5.5,Artificial Analysis - Claude Opus 5.5 (low with fallback),,False,Artificial Analysis,low,,31.3131,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:11dc57e4e600b27d,aa_terminal_bench_4,gpt-6.1-sol,Artificial Analysis - GPT-6.1 Sol (low),,False,Artificial Analysis,low,,30.8081,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:ba48609dee4ff716,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (xhigh),,False,Artificial Analysis,xhigh,,30.303,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:290fa3a81acd0ea0,aa_terminal_bench_4,claude-sonnet-5.5,Artificial Analysis - Claude Sonnet 5.5 (medium with fallback),,False,Artificial Analysis,medium,,29.798,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:1e5a05b16aa7028a,aa_terminal_bench_4,deepseek-v4.1-flash,Artificial Analysis - DeepSeek V4.1 Flash (max),,False,Artificial Analysis,max,,26.7677,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a61fb5355f7888c8,aa_terminal_bench_4,claude-opus-5,Artificial Analysis - Claude Opus 5 (low),,False,Artificial Analysis,low,,26.2626,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2ac75acfdd5556ef,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (high),,False,Artificial Analysis,high,,26.2626,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:24968b82abf21817,aa_terminal_bench_4,grok-4.7,Artificial Analysis - Grok 4.7 (xhigh),,False,Artificial Analysis,xhigh,,25.7576,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:131082f722734b10,aa_terminal_bench_4,grok-4.7,Artificial Analysis - Grok 4.7 (high),,False,Artificial Analysis,high,,24.7475,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:f850c291e94d4eee,aa_terminal_bench_4,gpt-5.6-sol,Artificial Analysis - GPT-5.6 Sol (xhigh),,False,Artificial Analysis,xhigh,,24.7475,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:f1477201d34edbb5,aa_terminal_bench_4,mimo-v2.6-flash,Artificial Analysis - MiMo-V2.6-Flash,,False,Artificial Analysis,,,22.7273,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:6569cb5d8342ed58,aa_terminal_bench_4,claude-opus-4.8,Artificial Analysis - Claude Opus 4.8 (max),,False,Artificial Analysis,max,,21.7172,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0493139313b0b012,aa_terminal_bench_4,grok-4.6,Artificial Analysis - Grok 4.6 (high),,False,Artificial Analysis,high,,21.2121,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:f0f6b217be9a4963,aa_terminal_bench_4,gpt-5.6-sol,Artificial Analysis - GPT-5.6 Sol (high),,False,Artificial Analysis,high,,20.7071,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4ae9b6951364c3e4,aa_terminal_bench_4,claude-sonnet-5.5,Artificial Analysis - Claude Sonnet 5.5 (low with fallback),,False,Artificial Analysis,low,,20.7071,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a1eae5d167a32a34,aa_terminal_bench_4,gemini-3.8-flash,Artificial Analysis - Gemini 3.8 Flash (medium),,False,Artificial Analysis,medium,,19.697,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0a0853cb96c8ece1,aa_terminal_bench_4,gemini-3.8-flash,Artificial Analysis - Gemini 3.8 Flash (high),,False,Artificial Analysis,high,,19.697,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0487a0a408dccb82,aa_terminal_bench_4,qwen3.8-max,Artificial Analysis - Qwen3.8 Max,,False,Artificial Analysis,max,,18.6869,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:5b54a5c8b54994f4,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (medium),,False,Artificial Analysis,medium,,18.6869,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:27d67549b5ee1d8d,aa_terminal_bench_4,grok-4.6,Artificial Analysis - Grok 4.6 (xhigh),,False,Artificial Analysis,xhigh,,17.1717,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:77d9a42a8772a37d,aa_terminal_bench_4,muse-spark-1.3,Artificial Analysis - Muse Spark 1.3 (xhigh),,False,Artificial Analysis,xhigh,,16.6667,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:b426d7104b617616,aa_terminal_bench_4,gpt-5.5,Artificial Analysis - GPT-5.5 (xhigh),,False,Artificial Analysis,xhigh,,14.6465,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:de8c4cd8b48f6964,aa_terminal_bench_4,gpt-5.6-sol,Artificial Analysis - GPT-5.6 Sol (medium),,False,Artificial Analysis,medium,,14.6465,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c2972229b7214dfc,aa_terminal_bench_4,deepseek-v4-pro,Artificial Analysis - DeepSeek V4 Pro (max),,False,Artificial Analysis,max,,14.6465,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8a2bf906a5cca32e,aa_terminal_bench_4,claude-sonnet-5,Artificial Analysis - Claude Sonnet 5 (max),,False,Artificial Analysis,max,,14.1414,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:92c8207e8ca30249,aa_terminal_bench_4,deepseek-v4-pro,Artificial Analysis - DeepSeek V4 Pro 0813 (max),,False,Artificial Analysis,max,,14.1414,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:69dd3b76427af507,aa_terminal_bench_4,gemini-3.7-flash,Artificial Analysis - Gemini 3.7 Flash (high),,False,Artificial Analysis,high,,13.6364,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:008592dee2abfbd4,aa_terminal_bench_4,grok-4.6,Artificial Analysis - Grok 4.6 (medium),,False,Artificial Analysis,medium,,13.1313,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:ba96dfd07fb6e2bc,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (non-reasoning),,False,Artificial Analysis,,,13.1313,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:cc7c150caad9b305,aa_terminal_bench_4,kimi-k3,Artificial Analysis - Kimi K3 (low),,False,Artificial Analysis,low,,12.6263,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4d4153eb38f2e84f,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (max),,False,Artificial Analysis,max,,12.6263,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a6ac642cac2ac396,aa_terminal_bench_4,kimi-k3,Artificial Analysis - Kimi K3 (max),,False,Artificial Analysis,max,,12.6263,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2bd2f5c3a28cefaa,aa_terminal_bench_4,deepseek-v4-flash-vision-exp,Artificial Analysis - DeepSeek V4 Flash Vision (max),,False,Artificial Analysis,max,,12.1212,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a807bd1873a40322,aa_terminal_bench_4,deepseek-v4-flash,Artificial Analysis - DeepSeek V4 Flash 0731 (max),,False,Artificial Analysis,max,,12.1212,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:9c11404866580c5d,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (max),,False,Artificial Analysis,max,,11.6162,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:68bfb23c4047a7a3,aa_terminal_bench_4,grok-4.5,Artificial Analysis - Grok 4.5 (high),,False,Artificial Analysis,high,,10.6061,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:653b68c5fe321a32,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (xhigh),,False,Artificial Analysis,xhigh,,10.101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:76b42aa2f87efd5c,aa_terminal_bench_4,gemini-3.8-flash,Artificial Analysis - Gemini 3.8 Flash (low),,False,Artificial Analysis,low,,10.101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:af9e50a31779df75,aa_terminal_bench_4,gpt-6-sol,Artificial Analysis - GPT-6 Sol (low),,False,Artificial Analysis,low,,9.0909,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:7bff670f3c107bb6,aa_terminal_bench_4,gpt-5.5,Artificial Analysis - GPT-5.5 (high),,False,Artificial Analysis,high,,9.0909,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:3956f4765e345bfa,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (xhigh),,False,Artificial Analysis,xhigh,,8.0808,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:af37ce7e1e85aaba,aa_terminal_bench_4,muse-spark-1.2,Artificial Analysis - Muse Spark 1.2 (xhigh),,False,Artificial Analysis,xhigh,,7.0707,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:ec826f6447a6ed8b,aa_terminal_bench_4,gemini-3.6-flash,Artificial Analysis - Gemini 3.6 Flash (high),,False,Artificial Analysis,high,,7.0707,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:58f8a2ad361cbfac,aa_terminal_bench_4,claude-sonnet-5,Artificial Analysis - Claude Sonnet 5 (xhigh),,False,Artificial Analysis,xhigh,,7.0707,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:5b3cd3f66e09bf91,aa_terminal_bench_4,deepseek-v4.1-flash,Artificial Analysis - DeepSeek V4.1 Flash (non-reasoning),,False,Artificial Analysis,,,5.5556,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c563447fe73f34f6,aa_terminal_bench_4,qwen3.8-27b,Artificial Analysis - Qwen3.8 27B (xhigh),,False,Artificial Analysis,xhigh,,5.5556,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:d9a51d09614610e8,aa_terminal_bench_4,qwen3.8-27b,Artificial Analysis - Qwen3.8 27B (medium),,False,Artificial Analysis,medium,,5.0505,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:52b22206889b7f5e,aa_terminal_bench_4,gpt-5.5,Artificial Analysis - GPT-5.5 (medium),,False,Artificial Analysis,medium,,5.0505,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4583c02c014dc3d1,aa_terminal_bench_4,claude-sonnet-5,Artificial Analysis - Claude Sonnet 5 (high),,False,Artificial Analysis,high,,5.0505,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:964384bb8d3b9a13,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (high),,False,Artificial Analysis,high,,4.5455,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:28b1f129442e7f1a,aa_terminal_bench_4,gemini-3.1-pro,Artificial Analysis - Gemini 3.1 Pro Preview,,False,Artificial Analysis,,,4.0404,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:79ab9eec86d38bba,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (xhigh),,False,Artificial Analysis,xhigh,,3.5354,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a2b58faa52397cc0,aa_terminal_bench_4,deepseek-v4-flash,Artificial Analysis - DeepSeek V4 Flash (high),,False,Artificial Analysis,high,,3.0303,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:ab17cc8e5487de99,aa_terminal_bench_4,grok-4.6,Artificial Analysis - Grok 4.6 (low),,False,Artificial Analysis,low,,3.0303,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0a46e136780aeec1,aa_terminal_bench_4,claude-sonnet-5,Artificial Analysis - Claude Sonnet 5 (low),,False,Artificial Analysis,low,,2.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:62b32b0accfdc3e1,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (medium),,False,Artificial Analysis,medium,,2.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a025952071adf945,aa_terminal_bench_4,qwen3.8-27b,Artificial Analysis - Qwen3.8 27B (low),,False,Artificial Analysis,low,,2.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:f7293c3aff3fb8b9,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (high),,False,Artificial Analysis,high,,2.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:fee6e8fd477b7ac8,aa_terminal_bench_4,deepseek-v4-flash,Artificial Analysis - DeepSeek V4 Flash (max),,False,Artificial Analysis,max,,2.5253,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:4f6bf2d4de391fa8,aa_terminal_bench_4,minimax-m3,Artificial Analysis - MiniMax-M3,,False,Artificial Analysis,,,2.0202,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:39ff8a3fc7a8b6c2,aa_terminal_bench_4,glm-5.1,Artificial Analysis - GLM-5.1,,False,Artificial Analysis,,,2.0202,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:eecd341c62332c35,aa_terminal_bench_4,claude-sonnet-5,Artificial Analysis - Claude Sonnet 5 (medium),,False,Artificial Analysis,medium,,2.0202,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c911fafd76fe1373,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (non-reasoning),,False,Artificial Analysis,,,1.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a3c02275461ec0cb,aa_terminal_bench_4,qwen3.7-max,Artificial Analysis - Qwen3.7 Max,,False,Artificial Analysis,max,,1.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8239d3088594c526,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (high),,False,Artificial Analysis,high,,1.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:b68acd500c6b4161,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (low),,False,Artificial Analysis,low,,1.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:79eac9decde86827,aa_terminal_bench_4,deepseek-v4-pro,Artificial Analysis - DeepSeek V4 Pro 0813 (non-reasoning),,False,Artificial Analysis,,,1.5152,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a5ddeab611927928,aa_terminal_bench_4,gpt-5.6-sol,Artificial Analysis - GPT-5.6 Sol (low),,False,Artificial Analysis,low,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:8b8fcc0fa14e07eb,aa_terminal_bench_4,inkling,Artificial Analysis - Inkling (xhigh),,False,Artificial Analysis,xhigh,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:9dda7394ba62eb25,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (medium),,False,Artificial Analysis,medium,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:d0b5249bef72ad97,aa_terminal_bench_4,inkling-small,Artificial Analysis - Inkling Small,,False,Artificial Analysis,,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:c9067f00834590ba,aa_terminal_bench_4,kimi-k2.7-code,Artificial Analysis - Kimi K2.7 Code,,False,Artificial Analysis,,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:3d9d54fa83beecde,aa_terminal_bench_4,qwen3.7-plus,Artificial Analysis - Qwen3.7 Plus,,False,Artificial Analysis,,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:a734c5ed959dfebb,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (non-reasoning),,False,Artificial Analysis,,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:9ad8c75e6b68658f,aa_terminal_bench_4,glm-5.2,Artificial Analysis - GLM-5.2 (max),,False,Artificial Analysis,max,,1.0101,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:ca3671e92d985c3e,aa_terminal_bench_4,kimi-k2.6,Artificial Analysis - Kimi K2.6,,False,Artificial Analysis,,,0.5051,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:1837d1adb8970232,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (medium),,False,Artificial Analysis,medium,,0.5051,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:3d0d41d5c6a6aa9b,aa_terminal_bench_4,nemotron-3-ultra,Artificial Analysis - Nemotron 3 Ultra,,False,Artificial Analysis,,,0.5051,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2aa44c238da36b9a,aa_terminal_bench_4,gpt-5.6-terra,Artificial Analysis - GPT-5.6 Terra (non-reasoning),,False,Artificial Analysis,,,0.5051,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:7e5e9735030b01c8,aa_terminal_bench_4,hy3,Artificial Analysis - Hy3,,False,Artificial Analysis,,,0.5051,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:bfe134e562d0cd53,aa_terminal_bench_4,mimo-v2.5-pro,Artificial Analysis - MiMo-V2.5-Pro,,False,Artificial Analysis,,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:2f7e69749a01454b,aa_terminal_bench_4,gpt-5.6-luna,Artificial Analysis - GPT-5.6 Luna (low),,False,Artificial Analysis,low,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:5a02fb72c74be509,aa_terminal_bench_4,mimo-v2.5,Artificial Analysis - MiMo-V2.5,,False,Artificial Analysis,,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:7f4fd5ee28b042c6,aa_terminal_bench_4,qwen3.8-27b,Artificial Analysis - Qwen3.8 27B (non-reasoning),,False,Artificial Analysis,,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:0ba9180d8eb1c0d7,aa_terminal_bench_4,minimax-m2.7,Artificial Analysis - MiniMax-M2.7,,False,Artificial Analysis,,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:d0a6a751fe4ac57c,aa_terminal_bench_4,longcat-2.0,Artificial Analysis - LongCat 2.0,,False,Artificial Analysis,,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:1f723b35d187e5ec,aa_terminal_bench_4,gpt-6-luna,Artificial Analysis - GPT-6 Luna (low),,False,Artificial Analysis,low,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_terminal_bench_4:d8495a02281ad221,aa_terminal_bench_4,mistral-medium-3.5,Artificial Analysis - Mistral Medium 3.5,,False,Artificial Analysis,medium,,0.0,,,,,https://artificialanalysis.ai/leaderboards/models,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:608ea08d36d3bc63,aa_coding_agent_index,claude-sonnet-5.5,Claude Code - Sonnet 5.5 (max),,False,Claude Code,max,,68.3578,,,14.1908,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:d3474ba216efd88d,aa_coding_agent_index,claude-opus-5.5,Claude Code - Opus 5.5 (max),,False,Claude Code,max,,65.9886,,,13.0364,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:9f60c3eaad821549,aa_coding_agent_index,gpt-6.1-sol,Codex - GPT-6.1 Sol (xhigh),,False,Codex,xhigh,,62.9078,,,1.0397,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:54bdbbcca087e6ff,aa_coding_agent_index,claude-sonnet-5.5,Claude Code - Sonnet 5.5 (xhigh),,False,Claude Code,xhigh,,62.8714,,,3.3334,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:f882189259104e87,aa_coding_agent_index,claude-fable-5.1,Claude Code - Fable 5.1 (max) (with fallback),,False,Claude Code,max,,62.2225,,,12.3881,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:1041b2cdd9886064,aa_coding_agent_index,claude-fable-5.1,Devin Fusion CLI - Claude Fable 5.1 XHigh + SWE-2 Medium,,False,Devin Fusion CLI,xhigh,,61.6826,,,7.8971,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:6ee94ff7d755eeee,aa_coding_agent_index,gpt-6-astra,Codex - GPT-6 Astra (max),,False,Codex,max,,61.645,,,7.4671,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:0e50f95e98c947c2,aa_coding_agent_index,gpt-6.1-sol,Codex - GPT-6.1 Sol (medium),,False,Codex,medium,,61.4147,,,0.7047,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:6adf1a461abaf0f2,aa_coding_agent_index,gpt-6.1-sol,Codex - GPT-6.1 Sol (high),,False,Codex,high,,60.1492,,,0.8892,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:718b49f369ed6f33,aa_coding_agent_index,gpt-6.1-sol,Codex - GPT-6.1 Sol (max),,False,Codex,max,,60.1475,,,1.5541,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:e0b71dfaa4f1714e,aa_coding_agent_index,claude-opus-5,Claude Code - Opus 5 (max),,False,Claude Code,max,,59.7264,,,10.7892,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:c64a6ebb32778718,aa_coding_agent_index,gpt-6-astra,Devin Fusion CLI - GPT-6 Astra XHigh + SWE-2 Medium,,False,Devin Fusion CLI,xhigh,,58.8884,,,4.5365,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:79db3062d86f1bbd,aa_coding_agent_index,gpt-6.1-sol,Codex - GPT-6.1 Sol (low),,False,Codex,low,,57.2163,,,0.4988,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:a5a1b714fe3ad343,aa_coding_agent_index,gpt-6-sol,Codex - GPT-6 Sol (max),,False,Codex,max,,56.6626,,,2.9897,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:fa75b2e79a4d8cb4,aa_coding_agent_index,grok-4.7,Grok Build - Grok 4.7 (xhigh),,False,Grok Build,xhigh,,56.2676,,,8.8175,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:197c477622a1763e,aa_coding_agent_index,claude-sonnet-5.5,Claude Code - Sonnet 5.5 (high),,False,Claude Code,high,,55.0125,,,1.2355,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:538ede13f4f0982c,aa_coding_agent_index,gpt-5.6-sol,Codex - GPT-5.6 Sol (max),,False,Codex,max,,54.5591,,,6.3533,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:36a45d40bcfc3714,aa_coding_agent_index,muse-spark-1.3,Muse Code - Muse Spark 1.3 (max),,False,Muse Code,max,,54.3027,,,3.9775,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:9f41ae70311c2b0b,aa_coding_agent_index,glm-5.3,Opencode - GLM-5.3,,False,Opencode,max,,53.5548,,,4.2414,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:4a7256426ed97ee6,aa_coding_agent_index,kimi-k3,Kimi Code CLI - Kimi K3,,False,Kimi Code CLI,,,51.9259,,,5.0472,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:2aeda79a0ee5dba5,aa_coding_agent_index,muse-spark-1.3,Muse Code - Muse Spark 1.3 (xhigh),,False,Muse Code 1.0.2 RC,xhigh,,48.2993,,,3.4678,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:1157285386872e0a,aa_coding_agent_index,grok-4.6,Grok Build - Grok 4.6 (xhigh),,False,Grok Build,xhigh,,46.969,,,3.5701,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:5b82e4f8ad6e49f3,aa_coding_agent_index,claude-sonnet-5.5,Claude Code - Sonnet 5.5 (medium),,False,Claude Code,medium,,45.884,,,0.6188,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:82bc37b4bd5aa375,aa_coding_agent_index,qwen3.8-max,Claude Code - Qwen3.8 Max,,False,Claude Code,max,,43.2653,,,3.479,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:cdca4b328af5e088,aa_coding_agent_index,gpt-5.6-luna,Codex - GPT-5.6 Luna (max),,False,Codex,max,,43.2247,,,0.438,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:d18f5779019b6787,aa_coding_agent_index,deepseek-v4-pro,Codex - DeepSeek V4 Pro 0813 (max),,False,Codex,max,,43.052,,,0.238,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:1f7a78464bab7071,aa_coding_agent_index,claude-sonnet-5.5,Claude Code - Sonnet 5.5 (low),,False,Claude Code,low,,42.0593,,,0.4831,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:68de21286728c605,aa_coding_agent_index,gemini-3.8-flash,Antigravity SDK - Gemini 3.8 Flash (high),,False,Antigravity SDK v0.1.12,high,,41.8632,,,2.4674,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:01e2ffcaa1665576,aa_coding_agent_index,gpt-6-luna,Codex - GPT-6 Luna (max),,False,Codex,max,,41.0744,,,0.1759,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json aa_coding_agent_index:77cf38495a1886a0,aa_coding_agent_index,deepseek-v4-flash,Codex - DeepSeek V4 Flash 0731 (max),,False,Codex,max,,38.7425,,,0.0851,,https://artificialanalysis.ai/agents/coding-agents,2026-10-01,scores-aa-round5-2026-10-01.json terminal_bench_4:e5bdec03718dfb8f,terminal_bench_4,gpt-6-astra,Codex - GPT-6 Astra (max),,False,Codex,max,,58.18,55.39,60.97,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:136537b36ce98c25,terminal_bench_4,claude-fable-5.1,Claude Code - Fable 5.1 (max),,False,Claude Code,max,,57.88,54.120000000000005,61.64,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:d1970c4faffe81bc,terminal_bench_4,gpt-6-astra,Codex - GPT-6 Astra (xhigh),,False,Codex,xhigh,,57.88,55.160000000000004,60.6,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:425d97cf71b364f9,terminal_bench_4,gpt-6-astra,Codex - GPT-6 Astra (high),,False,Codex,high,,57.88,54.910000000000004,60.85,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:cc67912665adccef,terminal_bench_4,claude-fable-5.1,Claude Code - Fable 5.1 (xhigh),,False,Claude Code,xhigh,,57.88,54.52,61.24,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:c1be8fa31509c696,terminal_bench_4,claude-fable-5.1,Claude Code - Fable 5.1 (high),,False,Claude Code,high,,54.55,51.11,57.989999999999995,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:1ebcc077b6f11845,terminal_bench_4,gpt-6-astra,Codex - GPT-6 Astra (medium),,False,Codex,medium,,54.24,51.58,56.900000000000006,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:5edd3a6853cd6339,terminal_bench_4,claude-fable-5.1,Claude Code - Fable 5.1 (medium),,False,Claude Code,medium,,53.94,50.55,57.33,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:7d59ed14e6a26f29,terminal_bench_4,claude-opus-5,Claude Code - Opus 5 (xhigh),,False,Claude Code,xhigh,,53.94,50.769999999999996,57.11,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:cec3b7db483cca26,terminal_bench_4,claude-opus-5,Claude Code - Opus 5 (max),,False,Claude Code,max,,51.82,48.43,55.21,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:6c09cda642c293be,terminal_bench_4,gpt-6-astra,Codex - GPT-6 Astra (low),,False,Codex,low,,50.61,47.86,53.36,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:82e30cded058a067,terminal_bench_4,claude-opus-5,Claude Code - Opus 5 (high),,False,Claude Code,high,,50.3,46.57,54.029999999999994,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:314e4521dd78b2f2,terminal_bench_4,claude-opus-5,Claude Code - Opus 5 (medium),,False,Claude Code,medium,,44.85,41.02,48.68,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:eb2874e55b9e0003,terminal_bench_4,claude-fable-5,Claude Code - Fable 5 (max),,False,Claude Code,max,,44.55,40.699999999999996,48.4,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:4bcb6aba27442f07,terminal_bench_4,claude-fable-5.1,Claude Code - Fable 5.1 (low),,False,Claude Code,low,,43.33,39.72,46.94,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:0bfd0655b217cb23,terminal_bench_4,glm-5.3,Claude Code - GLM-5.3 (max),,False,Claude Code,max,,41.82,38.59,45.05,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:bb8c22faf493862e,terminal_bench_4,grok-4.7,Grok Build - Grok 4.7 (xhigh),,False,Grok Build,xhigh,,37.58,34.04,41.12,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:52ccc5571264dbe4,terminal_bench_4,gpt-5.6-sol,Codex - GPT-5.6 Sol (max),,False,Codex,max,,37.27,33.49,41.050000000000004,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:3ef9fcfb65e0cb76,terminal_bench_4,claude-opus-5,Claude Code - Opus 5 (low),,False,Claude Code,low,,34.85,30.91,38.79,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:4b4e1e5e2f86b9f3,terminal_bench_4,claude-opus-4.8,Claude Code - Opus 4.8 (max),,False,Claude Code,max,,23.64,20.080000000000002,27.2,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:57a5da2cde308af0,terminal_bench_4,gpt-5.6-terra,Codex - GPT-5.6 Terra (max),,False,Codex,max,,21.52,18.27,24.77,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:2c30600255377a7d,terminal_bench_4,grok-4.6,Grok Build - Grok 4.6 (high),,False,Grok Build,high,,20.3,17.21,23.39,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:206ddf92cd474c5f,terminal_bench_4,gemini-3.8-flash,mini-SWE-agent - Gemini 3.8 Flash (high),,False,mini-SWE-agent,high,,19.09,15.73,22.45,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:0b68373ce672d59b,terminal_bench_4,gpt-5.6-luna,Codex - GPT-5.6 Luna (max),,False,Codex,max,,17.27,14.42,20.12,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:98d088ff379b956d,terminal_bench_4,grok-4.5,Grok Build - Grok 4.5 (high),,False,Grok Build,high,,12.42,9.8,15.04,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:5718a86e9278cdf2,terminal_bench_4,claude-sonnet-5,Claude Code - Sonnet 5 (max),,False,Claude Code,max,,12.42,9.36,15.48,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:2106790cd4627629,terminal_bench_4,gemini-3.7-flash,mini-SWE-agent - Gemini 3.7 Flash (high),,False,mini-SWE-agent,high,,11.21,8.760000000000002,13.66,,,https://www.tbench.ai/leaderboard,2026-10-01,scores-terminal-bench4-round3-2026-10-01.json terminal_bench_4:b14874c72f248246,terminal_bench_4,deepseek-v4.1-flash,DeepSeek Harness Minimal - DeepSeek V4.1 Flash (max) [vendor self-report],,True,DeepSeek Harness Minimal,max,,31.2,,,,,https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash,2026-09-12,scores-terminal-bench4-selfreport-carry-2026-10-01.json terminal_bench_4:1852bc281e1867f4,terminal_bench_4,swe-2,Devin CLI - SWE-2 (best effort) [vendor self-report],,True,Devin CLI,,,27.3,,,,,https://cognition.com/blog/swe-2,2026-09-12,scores-terminal-bench4-selfreport-carry-2026-10-01.json terminal_bench_4:7939bf883e242fa9,terminal_bench_4,claude-opus-5.5,Claude Code - Claude Opus 5.5 (default) - self-reported [vendor self-report],,True,Claude Code,,,66.4,,,,,https://www.anthropic.com/claude-opus-5-5,2026-09-23,scores-terminal-bench4-selfreport-carry-2026-10-01.json arena_code:1eb4c01b2d86e5d0,arena_code,claude-opus-5.5,claude-opus-5.5-max,,False,,max,,1818,1801.5,1834.5,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:2fa5b191581aaf87,arena_code,gpt-6-astra,gpt-6-astra-max,,False,,max,,1789,1778.6,1799.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:8cc100910da385f3,arena_code,gpt-6.1-sol,gpt-6.1-sol-max,,False,,max,,1759,1739.9,1778.1,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:8e70472a84bf71d1,arena_code,claude-fable-5.1,claude-fable-5.1-max,,False,,max,,1751,1741.3,1760.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:c72d3ba206f54fd5,arena_code,claude-sonnet-5.5,claude-sonnet-5.5-high,,False,,high,,1709,1693.4,1724.6,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:3aa3e36faa602970,arena_code,claude-opus-5,claude-opus-5-max,,False,,max,,1694,1687.5,1700.5,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:99658ae7db6b17a4,arena_code,gpt-6-sol,gpt-6-sol-max,,False,,max,,1689,1677.2,1700.8,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:ab7cf4e12f67d532,arena_code,qwen3.8-max,qwen3.8-max,,False,,max,,1671,1659.0,1683.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:8f7b0b66ed443b08,arena_code,qwen3.8-max-0902,qwen3.8-max-0902,,False,,max,,1670,1662.0,1678.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:6b8714542169429d,arena_code,claude-opus-5,claude-opus-5-high,,False,,high,,1660,1654.3,1665.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:ac2bf8a87d9de607,arena_code,kimi-k3,kimi-k3-max,,False,,max,,1658,1651.6,1664.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:d79805eb17b0ddce,arena_code,muse-spark-1.3,muse-spark-1.3-max,,False,,max,,1655,1646.3,1663.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:168968cc57cebb7d,arena_code,grok-4.7,grok-4.7-xhigh,,False,,xhigh,,1636,1624.0,1648.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:a9cb90573e973a11,arena_code,hy4-preview,hy4-preview,,False,,,,1633,1623.6,1642.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:72ebbd507122c58e,arena_code,claude-fable-5,claude-fable-5-high,,False,,high,,1626,1619.6,1632.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:795cc8453d3a1a24,arena_code,muse-spark-1.3,muse-spark-1.3 (xHigh),,False,,xhigh,,1623,1614.2,1631.8,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:2d279d541bee2ba7,arena_code,glm-5.3,glm-5.3-max,,False,,max,,1622,1613.8,1630.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:dec9c8da0773c02d,arena_code,grok-4.6,grok-4.6-high,,False,,high,,1620,1612.1,1627.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:4e5d5fbc5aef2e52,arena_code,deepseek-v4.1-flash,deepseek-v4.1-flash-max,,False,,max,,1620,1609.6,1630.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:7e9fde485c6ddc62,arena_code,gpt-5.6-sol,gpt-5.6-sol-xhigh (codex-harness),,False,Codex,xhigh,,1619,1613.0,1625.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:8f9ded4c04cd93a8,arena_code,mimo-v2.6-pro,mimo-v2.6-pro,,False,,,,1619,1606.8,1631.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:379b30f1d5942d86,arena_code,glm-5.3-flash,glm-5.3-flash,,False,,,,1615,1607.3,1622.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:828ee7654a1873aa,arena_code,glm-5.2,glm-5.2-max,,False,,max,,1605,1598.6,1611.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:778f5c97eb827e03,arena_code,gemini-3.7-flash,gemini-3.7-flash-high,,False,,high,,1592,1584.6,1599.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:b8dc0ef18e30c1dc,arena_code,qwen3.8-27b,qwen3.8-27b,,False,,,,1590,1583.0,1597.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:cee78179b654f666,arena_code,gemini-3.8-flash,gemini-3.8-flash-high,,False,,high,,1583,1575.1,1590.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:986ec1bc7da59bd9,arena_code,deepseek-v4-pro,deepseek-v4-pro-high-20260813,,False,,high,,1582,1572.7,1591.3,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:27376aa104f48f0e,arena_code,gpt-6-luna,gpt-6-luna-max,,False,,max,,1582,1573.0,1591.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:672fd54eff364145,arena_code,deepseek-v4-flash,deepseek-v4-flash-high,,False,,high,,1581,1571.8,1590.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:5ebff85aa1280e1f,arena_code,step-5-preview,step-5-preview-high,,False,,high,,1570,1556.8,1583.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:fae8bb30a0d7476b,arena_code,claude-opus-4.8,claude-opus-4-8-high,,False,,high,,1556,1550.3,1561.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:dc0921a30ecddd2c,arena_code,grok-4.5,grok-4.5,,False,,,,1552,1545.4,1558.6,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:c91ce134bd5ec2e3,arena_code,claude-sonnet-5,claude-sonnet-5-high,,False,,high,,1540,1533.8,1546.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:4b88e3c88227052e,arena_code,gemini-3.6-flash,gemini-3.6-flash-high,,False,,high,,1536,1528.5,1543.5,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:00f9bf3b98edb73a,arena_code,claude-opus-4.8,claude-opus-4-8,,False,,,,1534,1528.3,1539.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:11c91ee348aca987,arena_code,muse-spark-1.2,muse-spark-1.2 (xHigh),,False,,xhigh,,1532,1518.4,1545.6,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:c67b556fb4592ef2,arena_code,gpt-5.6-terra,gpt-5.6-terra-xhigh (codex-harness),,False,Codex,xhigh,,1519,1512.4,1525.6,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:fbd75732eebb198a,arena_code,gpt-5.6-luna,gpt-5.6-luna-xhigh (codex-harness),,False,Codex,xhigh,,1518,1511.6,1524.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:ab16d803c029884c,arena_code,qwen3.7-max,qwen3.7-max-20260517,,False,,max,,1515,1507.6,1522.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:8bba805c5e778260,arena_code,gpt-5.5,gpt-5.5-xhigh (codex-harness),,False,Codex,xhigh,,1512,1506.1,1517.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:b806900ce18f190d,arena_code,kimi-k2.6,kimi-k2.6,,False,,,,1509,1501.8,1516.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:19874ad7a301d76d,arena_code,glm-5.1,glm-5.1,,False,,,,1508,1501.2,1514.8,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:c23c1b85207e0226,arena_code,hy3,hy3,,False,,,,1508,1499.3,1516.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:debea18029954afc,arena_code,gpt-5.5,gpt-5.5-high (codex-harness),,False,Codex,high,,1487,1481.1,1492.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:f206c3043bc8027f,arena_code,minimax-m3,minimax-m3,,False,,,,1482,1476.3,1487.7,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:efbac4e58b06eb10,arena_code,qwen3.6-max-preview,qwen3.6-max-preview,,False,,max,,1482,1469.5,1494.5,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:9e023543b5154b09,arena_code,mimo-v2.5-pro,mimo-v2.5-pro,,False,,,,1477,1471.6,1482.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:24e3159d841ef7a4,arena_code,kimi-k2.7-code,kimi-k2.7-code,,False,,,,1473,1463.6,1482.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:e98573cb34bd81ce,arena_code,deepseek-v4-pro,deepseek-v4-pro-high-preview,,False,,high,,1463,1456.7,1469.3,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:b7e5e5b8df1a65a0,arena_code,qwen3.6-plus,qwen3.6-plus,,False,,,,1461,1455.4,1466.6,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:d0396ac7d382d35b,arena_code,gpt-5.5,gpt-5.5 (codex-harness),,False,Codex,,,1455,1449.1,1460.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:ccbd7f0883547751,arena_code,gemini-3.1-pro,gemini-3.1-pro-preview,,False,,,,1446,1441.0,1451.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:fec2568cdfba26c6,arena_code,deepseek-v4-pro,deepseek-v4-pro,,False,,,,1446,1439.7,1452.3,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:101c12e441513d87,arena_code,mimo-v2.5,mimo-v2.5,,False,,,,1438,1432.0,1444.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:79ddd44617f3ec62,arena_code,kimi-k2.5,kimi-k2.5-thinking,,False,,thinking,,1436,1430.8,1441.2,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:1744764b0671d723,arena_code,glm-5,glm-5,,False,,,,1434,1425.9,1442.1,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:f3628e90994fda44,arena_code,deepseek-v4-flash,deepseek-v4-flash-high-preview,,False,,high,,1430,1423.1,1436.9,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:07b745ae2862d994,arena_code,inkling,inkling,,False,,,,1412,1405.6,1418.4,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:5e9cc8edc5997bcf,arena_code,inkling-small,Inkling Small,,False,,,,1408,1399.0,1417.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:cbe1c293dbc12cfd,arena_code,kimi-k2.5,kimi-k2.5-instant,,False,,,,1404,1392.0,1416.0,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:891df129a594a41e,arena_code,minimax-m2.7,minimax-m2.7,,False,,,,1397,1391.2,1402.8,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:28d1b5355f79eb7b,arena_code,minimax-m2.5,minimax-m2.5,,False,,,,1386,1377.7,1394.3,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_code:daa8896f14bb8dc8,arena_code,mistral-medium-3.5,mistral-medium-3.5,,False,,medium,,1263,1248.2,1277.8,,,https://arena.ai/leaderboard/code,2026-10-01,scores-code-arena-round2-2026-10-01.json arena_agent_mode:d1cdd70383ae2039,arena_agent_mode,claude-fable-5.1,Claude Fable 5.1 (Max),,False,,max,,14.55,12.63,16.47,,4.44,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:b1592396c4d6d498,arena_agent_mode,claude-opus-5.5,Claude Opus 5.5 (High),,False,,high,,13.78,11.54,16.02,,1.57,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:704fea58650c673b,arena_agent_mode,gpt-6-astra,GPT 6 Astra (Max),,False,,max,,12.18,9.9,14.459999999999999,,2.9,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:c3f5ba38fbb30407,arena_agent_mode,gpt-6-sol,GPT 6 Sol (Max),,False,,max,,10.65,8.08,13.22,,0.91,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:63ab115851e0de58,arena_agent_mode,claude-opus-5,Claude Opus 5 (High),,False,,high,,8.76,7.26,10.26,,2.5,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:7b426212aba5971e,arena_agent_mode,claude-opus-5,Claude Opus 5 (Max),,False,,max,,8.55,6.98,10.120000000000001,,3.59,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:3d3ae04ef0c99602,arena_agent_mode,claude-fable-5,Claude Fable 5 (High),,False,,high,,8.37,7.069999999999999,9.67,,2.02,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:5c55fe7f551fe2c6,arena_agent_mode,gpt-5.6-sol,GPT 5.6 Sol (xHigh),,False,,xhigh,,7.05,5.67,8.43,,1.05,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:263865305f7ecdb7,arena_agent_mode,claude-opus-4.8,Claude Opus 4.8 (High),,False,,high,,6.92,5.54,8.3,,1.36,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:5729b5a20a335dfc,arena_agent_mode,claude-sonnet-5,Claude Sonnet 5 (High),,False,,high,,4.81,3.09,6.529999999999999,,0.9,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:edee122a50e59a89,arena_agent_mode,hy4-preview,Hy4 preview,,False,,,,4.24,3.39,5.09,,0.29,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:0d8b2c85e74d262f,arena_agent_mode,muse-spark-1.3,Muse Spark 1.3 (Max),,False,,max,,4.19,3.6000000000000005,4.78,,0.41,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:605f40536c85bbb4,arena_agent_mode,gpt-5.5,GPT 5.5 (xHigh),,False,,xhigh,,4.12,3.0700000000000003,5.17,,1.22,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:c8965e5dd2526f05,arena_agent_mode,deepseek-v4.1-flash,Deepseek V4.1 Flash (Max),,False,,max,,4.01,3.51,4.51,,0.09,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:1307216843d89276,arena_agent_mode,kimi-k3,Kimi K3 (Max),,False,,max,,3.98,3.45,4.51,,0.75,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:0684f9cc2a945bdb,arena_agent_mode,grok-4.7,Grok 4.7 (xHigh),,False,,xhigh,,3.64,2.0700000000000003,5.21,,1.47,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:f4f60f98940c49ee,arena_agent_mode,glm-5.2,GLM 5.2 (Max),,False,,max,,3.64,2.9000000000000004,4.38,,0.76,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:60a00778bc1492a5,arena_agent_mode,gemini-3.8-flash,Gemini 3.8 Flash (High),,False,,high,,2.96,2.14,3.78,,0.58,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:9ce366a4c245bae4,arena_agent_mode,qwen3.8-max,Qwen3.8 Max,,False,,max,,2.8,2.15,3.4499999999999997,,0.44,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:64885804c8dddecd,arena_agent_mode,glm-5.3,GLM 5.3 (Max),,False,,max,,2.57,1.8499999999999999,3.29,,0.64,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:04bd9ba65c143398,arena_agent_mode,gpt-6-luna,GPT 6 Luna (Max),,False,,max,,1.68,0.27,3.09,,0.06,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:3081d8b084b897bf,arena_agent_mode,deepseek-v4-pro,DeepSeek V4 Pro (High) (0813),,False,,high,,1.29,-0.4099999999999999,2.99,,0.38,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:09fac21036f59279,arena_agent_mode,grok-4.6,Grok 4.6 (xHigh),,False,,xhigh,,1.16,0.1399999999999999,2.1799999999999997,,0.99,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:f89b60d1061b77e1,arena_agent_mode,gpt-5.5,GPT 5.5,,False,,,,1.13,0.15999999999999992,2.0999999999999996,,0.61,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:069dfce97d9ef41d,arena_agent_mode,grok-4.5,Grok 4.5,,False,,,,1.11,0.1200000000000001,2.1,,0.44,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:96e32efd63046574,arena_agent_mode,gpt-5.6-terra,GPT 5.6 Terra (xHigh),,False,,xhigh,,0.83,-0.42000000000000004,2.08,,0.43,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:bd0ff69aca5acca9,arena_agent_mode,glm-5.3-flash,GLM 5.3 Flash,,False,,,,-0.28,-0.76,0.19999999999999996,,0.1,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:8455f3eb58f47b3d,arena_agent_mode,gpt-5.6-luna,GPT 5.6 Luna (xHigh),,False,,xhigh,,-1.09,-1.79,-0.3900000000000001,,0.07,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:22652d46f50fe772,arena_agent_mode,qwen3.8-27b,Qwen 3.8 27B,,False,,,,-1.61,-2.21,-1.0100000000000002,,0.31,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:47cad90e68374509,arena_agent_mode,gemini-3.7-flash,Gemini 3.7 Flash (High),,False,,high,,-1.64,-2.4,-0.8799999999999999,,0.38,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:84c2affbfb9336da,arena_agent_mode,muse-spark-1.2,Muse Spark 1.2 (xHigh),,False,,xhigh,,-2.96,-3.65,-2.27,,0.4,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:15166add541e68d5,arena_agent_mode,qwen3.7-max,Qwen3.7 Max,,False,,max,,-5.2,-6.140000000000001,-4.26,,0.19,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:3a37aca313fcd27d,arena_agent_mode,hy3,Hy3,,False,,,,-5.7,-6.93,-4.470000000000001,,0.04,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:a16fe8d7c7b78883,arena_agent_mode,minimax-m3,Minimax M3,,False,,,,-6.71,-7.6,-5.82,,0.08,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:c6879efca1b5dffc,arena_agent_mode,mimo-v2.5-pro,Mimo V2.5 Pro,,False,,,,-7.23,-8.14,-6.32,,0.04,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:9cf4eb892a450683,arena_agent_mode,qwen3.7-plus,Qwen3.7 Plus,,False,,,,-7.28,-8.75,-5.8100000000000005,,0.09,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:46d0083fa34f1126,arena_agent_mode,gemini-3.1-pro,Gemini 3.1 Pro Preview,,False,,,,-7.35,-8.33,-6.369999999999999,,0.29,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:ee3d29f57f6b6e33,arena_agent_mode,gemini-3.6-flash,Gemini 3.6 Flash (High),,False,,high,,-7.67,-8.75,-6.59,,0.3,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:03dbaa1180987af9,arena_agent_mode,inkling-small,Inkling Small,,False,,,,-9.8,-11.22,-8.38,,0.1,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:8967f33635820f8b,arena_agent_mode,inkling,Inkling,,False,,,,-10.9,-11.96,-9.84,,0.25,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json arena_agent_mode:9c4432eeedad5bad,arena_agent_mode,mistral-medium-3.5,Mistral Medium 3.5,,False,,medium,,-11.74,-13.24,-10.24,,0.67,https://arena.ai/leaderboard/agent,2026-10-01,scores-agent-arena-round2-2026-10-01.json open_design_arena:1f49b4d125f7e8d5,open_design_arena,gpt-6.1-sol,GPT-6.1 Sol,,False,OpenDesign,,,90.1,,,0.38203,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:63b060c2709bd850,open_design_arena,gpt-6-sol,GPT-6 Sol,,False,OpenDesign,,,89.9,,,0.296641,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:5d69f844da6dc80d,open_design_arena,claude-sonnet-5.5,Claude Sonnet 5.5,,False,OpenDesign,,,86.8,,,0.573814,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:af24dbf7d52582a5,open_design_arena,mimo-v2.6-flash,MiMo 2.6 Flash,,False,OpenDesign,,,83.5,,,0.02894,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:df380d7af56a8dd0,open_design_arena,gpt-6-luna,GPT-6 Luna,,False,OpenDesign,,,83.1,,,0.015871,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:91957ddea79bc27b,open_design_arena,grok-4.7,Grok 4.7,,False,OpenDesign,,,82.9,,,0.662291,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:eab6a68a5b32527b,open_design_arena,gpt-6-astra,GPT-6 Astra,,False,OpenDesign,,,82.7,,,1.612939,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:050e7234636e98be,open_design_arena,deepseek-v4.1-flash,DeepSeek V4.1 Flash,,False,OpenDesign,,,81.2,,,0.023264,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:0ed675e0b61ae3ac,open_design_arena,claude-fable-5.1,Claude Fable 5.1,,False,OpenDesign,,,80.3,,,3.660199,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:e7590d5e99a8809f,open_design_arena,glm-5.3-flashx,GLM-5.3 Flash-X,,False,OpenDesign,,,80.1,,,0.097833,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:048a6b75c77d30fe,open_design_arena,gpt-5.6-sol,GPT-5.6 Sol,,False,OpenDesign,,,77.6,,,0.544242,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:1d059a6d807d4308,open_design_arena,hy4-preview,Hunyuan H4 Preview,,False,OpenDesign,,,74.6,,,0.417793,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:fbd3d33fa1d7cf9a,open_design_arena,qwen3.8-max,Qwen 3.8-Max,,False,OpenDesign,max,,72,,,0.595399,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:e5b1ca76e59dabd0,open_design_arena,gemini-3.8-flash,Gemini 3.8 Flash,,False,OpenDesign,,,68.9,,,0.210201,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:3d2b13f88b32b8ff,open_design_arena,muse-spark-1.3,Muse Spark 1.3,,False,OpenDesign,,,66.6,,,0.267309,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json open_design_arena:9aadc4d724514f03,open_design_arena,kimi-k3,Kimi K3,,False,OpenDesign,,,65.7,,,0.613653,,https://open-design.ai/zh/llm-arena-for-design/,2026-10-01,scores-open-design-round2-2026-10-01.json