{
  "question_count": 70,
  "points_per_question": 100,
  "maximum_total_score": 7000,
  "generated_at": "2026-10-12T08:49:12+00:00",
  "official": false,
  "category_counts": {
    "planning_single": 36,
    "recommendation_single": 21,
    "staged": 13
  },
  "ranking": [
    {
      "rank": 1,
      "model": "GPT Sol",
      "question_count": 70,
      "total_score_interval": [
        5535.28,
        5535.28
      ],
      "mean_score_interval": [
        79.07542857142857,
        79.07542857142857
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            1025.78,
            1025.78
          ],
          "mean_score_interval": [
            48.846666666666664,
            48.846666666666664
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            3303.5,
            3303.5
          ],
          "mean_score_interval": [
            91.76388888888889,
            91.76388888888889
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            1206.0,
            1206.0
          ],
          "mean_score_interval": [
            92.76923076923077,
            92.76923076923077
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 2,
      "model": "GPT Astra",
      "question_count": 70,
      "total_score_interval": [
        5485.17,
        5485.17
      ],
      "mean_score_interval": [
        78.35957142857143,
        78.35957142857143
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            1054.67,
            1054.67
          ],
          "mean_score_interval": [
            50.22238095238095,
            50.22238095238095
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            3257.5,
            3257.5
          ],
          "mean_score_interval": [
            90.48611111111111,
            90.48611111111111
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            1173.0,
            1173.0
          ],
          "mean_score_interval": [
            90.23076923076923,
            90.23076923076923
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 3,
      "model": "DeepSeek V4.1 Flash",
      "question_count": 70,
      "total_score_interval": [
        4771.035263157894,
        4771.035263157894
      ],
      "mean_score_interval": [
        68.15764661654136,
        68.15764661654136
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            1092.93,
            1092.93
          ],
          "mean_score_interval": [
            52.044285714285714,
            52.044285714285714
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2629.6052631578946,
            2629.6052631578946
          ],
          "mean_score_interval": [
            73.04459064327486,
            73.04459064327486
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            1048.5,
            1048.5
          ],
          "mean_score_interval": [
            80.65384615384616,
            80.65384615384616
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 4,
      "model": "GLM 5.3 Flash",
      "question_count": 70,
      "total_score_interval": [
        4676.17,
        4676.17
      ],
      "mean_score_interval": [
        66.80242857142858,
        66.80242857142858
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            1028.17,
            1028.17
          ],
          "mean_score_interval": [
            48.96047619047619,
            48.96047619047619
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2550.0,
            2550.0
          ],
          "mean_score_interval": [
            70.83333333333333,
            70.83333333333333
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            1098.0,
            1098.0
          ],
          "mean_score_interval": [
            84.46153846153847,
            84.46153846153847
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 5,
      "model": "Qwen3.8 Max",
      "question_count": 70,
      "total_score_interval": [
        4496.92,
        4496.92
      ],
      "mean_score_interval": [
        64.24171428571428,
        64.24171428571428
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            980.92,
            980.92
          ],
          "mean_score_interval": [
            46.71047619047619,
            46.71047619047619
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2572.0,
            2572.0
          ],
          "mean_score_interval": [
            71.44444444444444,
            71.44444444444444
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            944.0,
            944.0
          ],
          "mean_score_interval": [
            72.61538461538461,
            72.61538461538461
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0,
      "extended_budget_seconds": 2400,
      "extended_replacement_count": 12,
      "new_attempt_timeout_count": 0,
      "new_attempt_failure_count": 0,
      "pending_node_count": 3,
      "extended_pending_answer_count": 0
    },
    {
      "rank": 6,
      "model": "Kimi K3",
      "question_count": 70,
      "total_score_interval": [
        4127.184736842105,
        4127.184736842105
      ],
      "mean_score_interval": [
        58.95978195488722,
        58.95978195488722
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            926.29,
            926.29
          ],
          "mean_score_interval": [
            44.10904761904762,
            44.10904761904762
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2249.8947368421054,
            2249.8947368421054
          ],
          "mean_score_interval": [
            62.49707602339181,
            62.49707602339181
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            951.0,
            951.0
          ],
          "mean_score_interval": [
            73.15384615384616,
            73.15384615384616
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 7,
      "model": "Gemini 3.8 Flash",
      "question_count": 70,
      "total_score_interval": [
        4076.0,
        4076.0
      ],
      "mean_score_interval": [
        58.22857142857143,
        58.22857142857143
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            925.0,
            925.0
          ],
          "mean_score_interval": [
            44.04761904761905,
            44.04761904761905
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2229.0,
            2229.0
          ],
          "mean_score_interval": [
            61.916666666666664,
            61.916666666666664
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            922.0,
            922.0
          ],
          "mean_score_interval": [
            70.92307692307692,
            70.92307692307692
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    },
    {
      "rank": 8,
      "model": "Gemini 3.1 Pro",
      "question_count": 70,
      "total_score_interval": [
        3888.67,
        3888.67
      ],
      "mean_score_interval": [
        55.55242857142857,
        55.55242857142857
      ],
      "categories": {
        "recommendation_single": {
          "question_count": 21,
          "total_score_interval": [
            876.67,
            876.67
          ],
          "mean_score_interval": [
            41.74619047619048,
            41.74619047619048
          ]
        },
        "planning_single": {
          "question_count": 36,
          "total_score_interval": [
            2091.0,
            2091.0
          ],
          "mean_score_interval": [
            58.083333333333336,
            58.083333333333336
          ]
        },
        "staged": {
          "question_count": 13,
          "total_score_interval": [
            921.0,
            921.0
          ],
          "mean_score_interval": [
            70.84615384615384,
            70.84615384615384
          ]
        }
      },
      "completed_count": 70,
      "timeout_count": 0,
      "completion_rate": 1.0,
      "pending_answer_count": 0
    }
  ],
  "score_note": {
    "zh-CN": "固定70题分母、按下界排序；超时计0，待核保留区间。区间只覆盖已登记未决点，教师复核状态逐条保留。",
    "en": "Fixed 70-task denominator and lower-bound ordering; timeouts score zero and pending points remain intervals. Intervals cover recorded unresolved points; teacher calibration remains pending."
  },
  "evidence_adjudication_note": "Eleven Gemini quality nodes have source-bound rulings; all selected 70-task scores are now determinate.",
  "selected_record_count": 560,
  "answer_text_available_count": 443,
  "new_result_answer_count": 124
}