[
 {
  "id": "31a478305c1641a6",
  "model": "openai/gpt-4o-2024-05-13",
  "status": "completed",
  "valid": 0,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "azure"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "experiment": {
    "label": "论文锚点复测 GPT-4o-2024-05-13 第2次"
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793102582798,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.78,
     "groups": {
      "memory": 3.88,
      "knowledge": 3.27,
      "persona": 4.11,
      "emotion": 3.17,
      "morality": 4.87,
      "believability": 3.13
     },
     "dims": {
      "mc": 3.88,
      "fa": 2.69,
      "bck": 3.85,
      "acb": 4.63,
      "ach": 4.27,
      "bcpb": 3.73,
      "bcph": 3.79,
      "es": 3.25,
      "er": 3.09,
      "ms": 4.91,
      "mr": 4.83,
      "hl": 3.09,
      "eg": 3.18
     },
     "ci": {
      "overall": [
       3.76,
       3.81
      ],
      "groups": {
       "memory": [
        3.76,
        4
       ],
       "knowledge": [
        3.19,
        3.36
       ],
       "persona": [
        4.07,
        4.14
       ],
       "emotion": [
        3.12,
        3.22
       ],
       "morality": [
        4.83,
        4.9
       ],
       "believability": [
        3.09,
        3.18
       ]
      }
     },
     "n": 6460
    },
    "zh": {
     "overall": 3.72,
     "groups": {
      "memory": 3.86,
      "knowledge": 3.29,
      "persona": 3.97,
      "emotion": 3.11,
      "morality": 4.83,
      "believability": 3.11
     },
     "dims": {
      "mc": 3.86,
      "fa": 2.76,
      "bck": 3.83,
      "acb": 4.54,
      "ach": 4.24,
      "bcpb": 3.47,
      "bcph": 3.61,
      "es": 3.19,
      "er": 3.03,
      "ms": 4.86,
      "mr": 4.79,
      "hl": 3.04,
      "eg": 3.18
     },
     "ci": {
      "overall": [
       3.69,
       3.76
      ],
      "groups": {
       "memory": [
        3.69,
        4.03
       ],
       "knowledge": [
        3.17,
        3.42
       ],
       "persona": [
        3.91,
        4.02
       ],
       "emotion": [
        3.03,
        3.18
       ],
       "morality": [
        4.77,
        4.87
       ],
       "believability": [
        3.05,
        3.17
       ]
      }
     },
     "n": 3230
    },
    "en": {
     "overall": 3.84,
     "groups": {
      "memory": 3.9,
      "knowledge": 3.26,
      "persona": 4.25,
      "emotion": 3.23,
      "morality": 4.91,
      "believability": 3.16
     },
     "dims": {
      "mc": 3.9,
      "fa": 2.63,
      "bck": 3.88,
      "acb": 4.73,
      "ach": 4.3,
      "bcpb": 3.99,
      "bcph": 3.96,
      "es": 3.31,
      "er": 3.14,
      "ms": 4.95,
      "mr": 4.88,
      "hl": 3.14,
      "eg": 3.17
     },
     "ci": {
      "overall": [
       3.81,
       3.88
      ],
      "groups": {
       "memory": [
        3.75,
        4.06
       ],
       "knowledge": [
        3.14,
        3.38
       ],
       "persona": [
        4.2,
        4.3
       ],
       "emotion": [
        3.14,
        3.3
       ],
       "morality": [
        4.88,
        4.94
       ],
       "believability": [
        3.1,
        3.22
       ]
      }
     },
     "n": 3230
    }
   },
   "excludedSessions": 34,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": false,
    "fullProtocol": false,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": "协议对照实验，只生成报告，不计入排行榜"
   }
  },
  "judged_samples": 6460
 },
 {
  "id": "47920340ab8e49fe",
  "model": "deepseek-v4-1-flash-261017",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {}
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793099687517,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.92,
     "groups": {
      "memory": 4.21,
      "knowledge": 3.55,
      "persona": 4.18,
      "emotion": 3.2,
      "morality": 4.79,
      "believability": 3.44
     },
     "dims": {
      "mc": 4.21,
      "fa": 3.12,
      "bck": 3.98,
      "acb": 4.66,
      "ach": 4.29,
      "bcpb": 3.78,
      "bcph": 4.01,
      "es": 3.25,
      "er": 3.15,
      "ms": 4.82,
      "mr": 4.76,
      "hl": 3.4,
      "eg": 3.49
     },
     "ci": {
      "overall": [
       3.9,
       3.94
      ],
      "groups": {
       "memory": [
        4.11,
        4.31
       ],
       "knowledge": [
        3.47,
        3.63
       ],
       "persona": [
        4.14,
        4.22
       ],
       "emotion": [
        3.14,
        3.26
       ],
       "morality": [
        4.76,
        4.83
       ],
       "believability": [
        3.41,
        3.48
       ]
      }
     },
     "n": 6488
    },
    "zh": {
     "overall": 3.87,
     "groups": {
      "memory": 4.23,
      "knowledge": 3.59,
      "persona": 4.03,
      "emotion": 3.16,
      "morality": 4.79,
      "believability": 3.42
     },
     "dims": {
      "mc": 4.23,
      "fa": 3.2,
      "bck": 3.98,
      "acb": 4.55,
      "ach": 4.24,
      "bcpb": 3.5,
      "bcph": 3.83,
      "es": 3.18,
      "er": 3.15,
      "ms": 4.82,
      "mr": 4.76,
      "hl": 3.39,
      "eg": 3.46
     },
     "ci": {
      "overall": [
       3.84,
       3.9
      ],
      "groups": {
       "memory": [
        4.07,
        4.37
       ],
       "knowledge": [
        3.47,
        3.71
       ],
       "persona": [
        3.98,
        4.08
       ],
       "emotion": [
        3.09,
        3.23
       ],
       "morality": [
        4.73,
        4.84
       ],
       "believability": [
        3.37,
        3.47
       ]
      }
     },
     "n": 3244
    },
    "en": {
     "overall": 3.96,
     "groups": {
      "memory": 4.19,
      "knowledge": 3.51,
      "persona": 4.34,
      "emotion": 3.23,
      "morality": 4.8,
      "believability": 3.46
     },
     "dims": {
      "mc": 4.19,
      "fa": 3.04,
      "bck": 3.98,
      "acb": 4.77,
      "ach": 4.34,
      "bcpb": 4.06,
      "bcph": 4.19,
      "es": 3.32,
      "er": 3.14,
      "ms": 4.83,
      "mr": 4.77,
      "hl": 3.41,
      "eg": 3.51
     },
     "ci": {
      "overall": [
       3.93,
       4
      ],
      "groups": {
       "memory": [
        4.05,
        4.32
       ],
       "knowledge": [
        3.41,
        3.64
       ],
       "persona": [
        4.29,
        4.39
       ],
       "emotion": [
        3.14,
        3.31
       ],
       "morality": [
        4.75,
        4.85
       ],
       "believability": [
        3.41,
        3.52
       ]
      }
     },
     "n": 3244
    }
   },
   "excludedSessions": 6,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6488
 },
 {
  "id": "7ec615d6637844cd",
  "model": "qwen-plus-character",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {}
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793104573610,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.77,
     "groups": {
      "memory": 3.79,
      "knowledge": 3.34,
      "persona": 4.08,
      "emotion": 3.09,
      "morality": 4.73,
      "believability": 3.29
     },
     "dims": {
      "mc": 3.79,
      "fa": 2.57,
      "bck": 4.11,
      "acb": 4.55,
      "ach": 4.22,
      "bcpb": 3.64,
      "bcph": 3.91,
      "es": 3.19,
      "er": 3,
      "ms": 4.82,
      "mr": 4.63,
      "hl": 3.27,
      "eg": 3.31
     },
     "ci": {
      "overall": [
       3.75,
       3.8
      ],
      "groups": {
       "memory": [
        3.67,
        3.91
       ],
       "knowledge": [
        3.26,
        3.42
       ],
       "persona": [
        4.04,
        4.12
       ],
       "emotion": [
        3.03,
        3.15
       ],
       "morality": [
        4.68,
        4.77
       ],
       "believability": [
        3.25,
        3.33
       ]
      }
     },
     "n": 6474
    },
    "zh": {
     "overall": 3.72,
     "groups": {
      "memory": 3.79,
      "knowledge": 3.43,
      "persona": 3.9,
      "emotion": 3.05,
      "morality": 4.71,
      "believability": 3.3
     },
     "dims": {
      "mc": 3.79,
      "fa": 2.73,
      "bck": 4.14,
      "acb": 4.43,
      "ach": 4.15,
      "bcpb": 3.36,
      "bcph": 3.66,
      "es": 3.1,
      "er": 3.01,
      "ms": 4.83,
      "mr": 4.58,
      "hl": 3.29,
      "eg": 3.31
     },
     "ci": {
      "overall": [
       3.69,
       3.75
      ],
      "groups": {
       "memory": [
        3.61,
        3.97
       ],
       "knowledge": [
        3.31,
        3.54
       ],
       "persona": [
        3.84,
        3.95
       ],
       "emotion": [
        2.98,
        3.13
       ],
       "morality": [
        4.64,
        4.77
       ],
       "believability": [
        3.24,
        3.36
       ]
      }
     },
     "n": 3237
    },
    "en": {
     "overall": 3.82,
     "groups": {
      "memory": 3.8,
      "knowledge": 3.25,
      "persona": 4.26,
      "emotion": 3.13,
      "morality": 4.74,
      "believability": 3.28
     },
     "dims": {
      "mc": 3.8,
      "fa": 2.41,
      "bck": 4.09,
      "acb": 4.66,
      "ach": 4.29,
      "bcpb": 3.93,
      "bcph": 4.16,
      "es": 3.27,
      "er": 2.98,
      "ms": 4.8,
      "mr": 4.68,
      "hl": 3.25,
      "eg": 3.32
     },
     "ci": {
      "overall": [
       3.79,
       3.85
      ],
      "groups": {
       "memory": [
        3.63,
        3.95
       ],
       "knowledge": [
        3.14,
        3.34
       ],
       "persona": [
        4.21,
        4.32
       ],
       "emotion": [
        3.05,
        3.21
       ],
       "morality": [
        4.68,
        4.81
       ],
       "believability": [
        3.22,
        3.34
       ]
      }
     },
     "n": 3237
    }
   },
   "excludedSessions": 20,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6474
 },
 {
  "id": "a9c1f7d7a75f4fb3",
  "model": "minimax/minimax-m2-her",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "minimax"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793099798625,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.59,
     "groups": {
      "memory": 3.79,
      "knowledge": 3.18,
      "persona": 3.72,
      "emotion": 3.06,
      "morality": 4.79,
      "believability": 2.95
     },
     "dims": {
      "mc": 3.79,
      "fa": 2.6,
      "bck": 3.76,
      "acb": 4.07,
      "ach": 4.01,
      "bcpb": 3.56,
      "bcph": 3.26,
      "es": 3.18,
      "er": 2.94,
      "ms": 4.79,
      "mr": 4.79,
      "hl": 2.86,
      "eg": 3.04
     },
     "ci": {
      "overall": [
       3.56,
       3.61
      ],
      "groups": {
       "memory": [
        3.67,
        3.9
       ],
       "knowledge": [
        3.09,
        3.26
       ],
       "persona": [
        3.68,
        3.77
       ],
       "emotion": [
        3.01,
        3.11
       ],
       "morality": [
        4.76,
        4.83
       ],
       "believability": [
        2.89,
        3
       ]
      }
     },
     "n": 6494
    },
    "zh": {
     "overall": 3.59,
     "groups": {
      "memory": 3.81,
      "knowledge": 3.26,
      "persona": 3.66,
      "emotion": 3,
      "morality": 4.77,
      "believability": 3.1
     },
     "dims": {
      "mc": 3.81,
      "fa": 2.77,
      "bck": 3.75,
      "acb": 3.99,
      "ach": 4.02,
      "bcpb": 3.43,
      "bcph": 3.19,
      "es": 3.08,
      "er": 2.93,
      "ms": 4.75,
      "mr": 4.78,
      "hl": 3.02,
      "eg": 3.18
     },
     "ci": {
      "overall": [
       3.56,
       3.63
      ],
      "groups": {
       "memory": [
        3.65,
        3.97
       ],
       "knowledge": [
        3.15,
        3.38
       ],
       "persona": [
        3.59,
        3.72
       ],
       "emotion": [
        2.94,
        3.07
       ],
       "morality": [
        4.71,
        4.82
       ],
       "believability": [
        3.02,
        3.18
       ]
      }
     },
     "n": 3247
    },
    "en": {
     "overall": 3.58,
     "groups": {
      "memory": 3.77,
      "knowledge": 3.1,
      "persona": 3.79,
      "emotion": 3.11,
      "morality": 4.82,
      "believability": 2.8
     },
     "dims": {
      "mc": 3.77,
      "fa": 2.42,
      "bck": 3.77,
      "acb": 4.15,
      "ach": 4.01,
      "bcpb": 3.69,
      "bcph": 3.32,
      "es": 3.28,
      "er": 2.95,
      "ms": 4.83,
      "mr": 4.81,
      "hl": 2.69,
      "eg": 2.9
     },
     "ci": {
      "overall": [
       3.55,
       3.62
      ],
      "groups": {
       "memory": [
        3.62,
        3.93
       ],
       "knowledge": [
        3,
        3.2
       ],
       "persona": [
        3.73,
        3.86
       ],
       "emotion": [
        3.03,
        3.19
       ],
       "morality": [
        4.77,
        4.87
       ],
       "believability": [
        2.72,
        2.87
       ]
      }
     },
     "n": 3247
    }
   },
   "excludedSessions": 0,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6494
 },
 {
  "id": "e279fdfe13874179",
  "model": "anthropic/claude-opus-5.5",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "anthropic"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793099858946,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.78,
     "groups": {
      "memory": 3.62,
      "knowledge": 3.42,
      "persona": 4.02,
      "emotion": 3.07,
      "morality": 4.78,
      "believability": 3.43
     },
     "dims": {
      "mc": 3.62,
      "fa": 2.89,
      "bck": 3.96,
      "acb": 4.43,
      "ach": 4.02,
      "bcpb": 3.65,
      "bcph": 3.97,
      "es": 3.05,
      "er": 3.09,
      "ms": 4.8,
      "mr": 4.77,
      "hl": 3.37,
      "eg": 3.49
     },
     "ci": {
      "overall": [
       3.76,
       3.8
      ],
      "groups": {
       "memory": [
        3.49,
        3.74
       ],
       "knowledge": [
        3.34,
        3.5
       ],
       "persona": [
        3.97,
        4.06
       ],
       "emotion": [
        3.01,
        3.12
       ],
       "morality": [
        4.74,
        4.82
       ],
       "believability": [
        3.39,
        3.48
       ]
      }
     },
     "n": 6476
    },
    "zh": {
     "overall": 3.71,
     "groups": {
      "memory": 3.58,
      "knowledge": 3.45,
      "persona": 3.86,
      "emotion": 2.99,
      "morality": 4.76,
      "believability": 3.43
     },
     "dims": {
      "mc": 3.58,
      "fa": 2.92,
      "bck": 3.97,
      "acb": 4.32,
      "ach": 3.93,
      "bcpb": 3.37,
      "bcph": 3.81,
      "es": 2.97,
      "er": 3.01,
      "ms": 4.77,
      "mr": 4.75,
      "hl": 3.36,
      "eg": 3.5
     },
     "ci": {
      "overall": [
       3.68,
       3.74
      ],
      "groups": {
       "memory": [
        3.4,
        3.75
       ],
       "knowledge": [
        3.33,
        3.57
       ],
       "persona": [
        3.8,
        3.91
       ],
       "emotion": [
        2.91,
        3.06
       ],
       "morality": [
        4.7,
        4.82
       ],
       "believability": [
        3.37,
        3.5
       ]
      }
     },
     "n": 3238
    },
    "en": {
     "overall": 3.84,
     "groups": {
      "memory": 3.65,
      "knowledge": 3.4,
      "persona": 4.18,
      "emotion": 3.15,
      "morality": 4.81,
      "believability": 3.44
     },
     "dims": {
      "mc": 3.65,
      "fa": 2.85,
      "bck": 3.96,
      "acb": 4.55,
      "ach": 4.11,
      "bcpb": 3.92,
      "bcph": 4.13,
      "es": 3.13,
      "er": 3.17,
      "ms": 4.82,
      "mr": 4.79,
      "hl": 3.39,
      "eg": 3.48
     },
     "ci": {
      "overall": [
       3.81,
       3.87
      ],
      "groups": {
       "memory": [
        3.49,
        3.81
       ],
       "knowledge": [
        3.29,
        3.51
       ],
       "persona": [
        4.12,
        4.23
       ],
       "emotion": [
        3.07,
        3.23
       ],
       "morality": [
        4.75,
        4.86
       ],
       "believability": [
        3.38,
        3.49
       ]
      }
     },
     "n": 3238
    }
   },
   "excludedSessions": 18,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6476
 },
 {
  "id": "e78e8134973f4bd5",
  "model": "openai/gpt-6-astra",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "openai/flex"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793099633494,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.83,
     "groups": {
      "memory": 3.89,
      "knowledge": 3.46,
      "persona": 4,
      "emotion": 3.19,
      "morality": 4.92,
      "believability": 3.35
     },
     "dims": {
      "mc": 3.89,
      "fa": 3.12,
      "bck": 3.8,
      "acb": 4.64,
      "ach": 4.03,
      "bcpb": 3.52,
      "bcph": 3.81,
      "es": 3.12,
      "er": 3.26,
      "ms": 4.93,
      "mr": 4.92,
      "hl": 3.26,
      "eg": 3.44
     },
     "ci": {
      "overall": [
       3.81,
       3.85
      ],
      "groups": {
       "memory": [
        3.78,
        4
       ],
       "knowledge": [
        3.38,
        3.55
       ],
       "persona": [
        3.96,
        4.03
       ],
       "emotion": [
        3.13,
        3.24
       ],
       "morality": [
        4.9,
        4.95
       ],
       "believability": [
        3.31,
        3.39
       ]
      }
     },
     "n": 6494
    },
    "zh": {
     "overall": 3.8,
     "groups": {
      "memory": 3.95,
      "knowledge": 3.5,
      "persona": 3.87,
      "emotion": 3.19,
      "morality": 4.91,
      "believability": 3.39
     },
     "dims": {
      "mc": 3.95,
      "fa": 3.17,
      "bck": 3.83,
      "acb": 4.56,
      "ach": 3.98,
      "bcpb": 3.32,
      "bcph": 3.61,
      "es": 3.1,
      "er": 3.28,
      "ms": 4.91,
      "mr": 4.91,
      "hl": 3.33,
      "eg": 3.45
     },
     "ci": {
      "overall": [
       3.77,
       3.83
      ],
      "groups": {
       "memory": [
        3.79,
        4.1
       ],
       "knowledge": [
        3.37,
        3.63
       ],
       "persona": [
        3.82,
        3.91
       ],
       "emotion": [
        3.11,
        3.26
       ],
       "morality": [
        4.87,
        4.94
       ],
       "believability": [
        3.33,
        3.44
       ]
      }
     },
     "n": 3247
    },
    "en": {
     "overall": 3.85,
     "groups": {
      "memory": 3.82,
      "knowledge": 3.42,
      "persona": 4.13,
      "emotion": 3.19,
      "morality": 4.93,
      "believability": 3.31
     },
     "dims": {
      "mc": 3.82,
      "fa": 3.07,
      "bck": 3.77,
      "acb": 4.71,
      "ach": 4.08,
      "bcpb": 3.72,
      "bcph": 4.01,
      "es": 3.14,
      "er": 3.24,
      "ms": 4.94,
      "mr": 4.93,
      "hl": 3.2,
      "eg": 3.43
     },
     "ci": {
      "overall": [
       3.82,
       3.88
      ],
      "groups": {
       "memory": [
        3.67,
        3.97
       ],
       "knowledge": [
        3.32,
        3.54
       ],
       "persona": [
        4.08,
        4.19
       ],
       "emotion": [
        3.12,
        3.26
       ],
       "morality": [
        4.91,
        4.96
       ],
       "believability": [
        3.26,
        3.37
       ]
      }
     },
     "n": 3247
    }
   },
   "excludedSessions": 0,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6494
 },
 {
  "id": "eebe847ae59b4d41",
  "model": "openai/gpt-4o-2024-05-13",
  "status": "completed",
  "valid": 0,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "azure"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "experiment": {
    "label": "论文锚点复测 GPT-4o-2024-05-13 第1次"
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793102548978,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.79,
     "groups": {
      "memory": 3.88,
      "knowledge": 3.34,
      "persona": 4.09,
      "emotion": 3.16,
      "morality": 4.86,
      "believability": 3.14
     },
     "dims": {
      "mc": 3.88,
      "fa": 2.85,
      "bck": 3.84,
      "acb": 4.68,
      "ach": 4.2,
      "bcpb": 3.71,
      "bcph": 3.78,
      "es": 3.23,
      "er": 3.1,
      "ms": 4.86,
      "mr": 4.85,
      "hl": 3.09,
      "eg": 3.19
     },
     "ci": {
      "overall": [
       3.77,
       3.81
      ],
      "groups": {
       "memory": [
        3.77,
        3.99
       ],
       "knowledge": [
        3.26,
        3.43
       ],
       "persona": [
        4.05,
        4.13
       ],
       "emotion": [
        3.11,
        3.21
       ],
       "morality": [
        4.83,
        4.89
       ],
       "believability": [
        3.09,
        3.18
       ]
      }
     },
     "n": 6462
    },
    "zh": {
     "overall": 3.73,
     "groups": {
      "memory": 3.93,
      "knowledge": 3.37,
      "persona": 3.94,
      "emotion": 3.14,
      "morality": 4.8,
      "believability": 3.11
     },
     "dims": {
      "mc": 3.93,
      "fa": 2.89,
      "bck": 3.86,
      "acb": 4.59,
      "ach": 4.14,
      "bcpb": 3.45,
      "bcph": 3.59,
      "es": 3.22,
      "er": 3.05,
      "ms": 4.79,
      "mr": 4.8,
      "hl": 3.04,
      "eg": 3.17
     },
     "ci": {
      "overall": [
       3.7,
       3.77
      ],
      "groups": {
       "memory": [
        3.75,
        4.11
       ],
       "knowledge": [
        3.25,
        3.5
       ],
       "persona": [
        3.89,
        3.99
       ],
       "emotion": [
        3.06,
        3.21
       ],
       "morality": [
        4.74,
        4.85
       ],
       "believability": [
        3.04,
        3.17
       ]
      }
     },
     "n": 3231
    },
    "en": {
     "overall": 3.84,
     "groups": {
      "memory": 3.83,
      "knowledge": 3.31,
      "persona": 4.24,
      "emotion": 3.19,
      "morality": 4.92,
      "believability": 3.17
     },
     "dims": {
      "mc": 3.83,
      "fa": 2.8,
      "bck": 3.83,
      "acb": 4.77,
      "ach": 4.26,
      "bcpb": 3.96,
      "bcph": 3.98,
      "es": 3.23,
      "er": 3.14,
      "ms": 4.92,
      "mr": 4.91,
      "hl": 3.13,
      "eg": 3.2
     },
     "ci": {
      "overall": [
       3.81,
       3.88
      ],
      "groups": {
       "memory": [
        3.65,
        3.99
       ],
       "knowledge": [
        3.21,
        3.43
       ],
       "persona": [
        4.19,
        4.3
       ],
       "emotion": [
        3.11,
        3.27
       ],
       "morality": [
        4.88,
        4.95
       ],
       "believability": [
        3.1,
        3.23
       ]
      }
     },
     "n": 3231
    }
   },
   "excludedSessions": 32,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": false,
    "fullProtocol": false,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": "协议对照实验，只生成报告，不计入排行榜"
   }
  },
  "judged_samples": 6462
 },
 {
  "id": "fb8c23842faa41d1",
  "model": "doubao-seed-character-260628",
  "status": "completed",
  "valid": 1,
  "protocol": "characterbench-2.0 · 2026-10-27",
  "datasetRevision": "66c113cf3c011697d4c232de6beabb7797a9a380",
  "judges": [
   {
    "key": "cj",
    "label": "CharacterJudge",
    "model": "thu-coai/CharacterJudge",
    "weight": 1,
    "enabled": true,
    "temperature": 0.7,
    "maxTokens": 512,
    "extra": {
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1.05
    },
    "kind": "score",
    "endpoint": "characterjudge",
    "concurrency": 100,
    "samples": 10
   }
  ],
  "engine": {
   "concurrency": 100,
   "maxRetries": 4,
   "requestTimeoutMs": 180000
  },
  "config": {
   "langs": [
    "zh",
    "en"
   ],
   "mode": "full",
   "targetParams": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "thinking": {
      "type": "disabled"
     }
    }
   },
   "expectedSessions": 6494,
   "rescored": {
    "version": "characterbench-2.0.1 · 2026-10-27",
    "from": "characterbench-2.0 · 2026-10-27",
    "at": 1793099740052,
    "sessions": 6494
   }
  },
  "result": {
   "perLang": {
    "all": {
     "overall": 3.82,
     "groups": {
      "memory": 4.05,
      "knowledge": 3.43,
      "persona": 4.01,
      "emotion": 3.17,
      "morality": 4.78,
      "believability": 3.4
     },
     "dims": {
      "mc": 4.05,
      "fa": 2.77,
      "bck": 4.09,
      "acb": 4.59,
      "ach": 4.28,
      "bcpb": 3.58,
      "bcph": 3.59,
      "es": 3.3,
      "er": 3.05,
      "ms": 4.8,
      "mr": 4.76,
      "hl": 3.38,
      "eg": 3.42
     },
     "ci": {
      "overall": [
       3.8,
       3.84
      ],
      "groups": {
       "memory": [
        3.94,
        4.16
       ],
       "knowledge": [
        3.35,
        3.51
       ],
       "persona": [
        3.97,
        4.05
       ],
       "emotion": [
        3.12,
        3.23
       ],
       "morality": [
        4.73,
        4.82
       ],
       "believability": [
        3.36,
        3.44
       ]
      }
     },
     "n": 6494
    },
    "zh": {
     "overall": 3.82,
     "groups": {
      "memory": 4.2,
      "knowledge": 3.52,
      "persona": 3.92,
      "emotion": 3.17,
      "morality": 4.75,
      "believability": 3.45
     },
     "dims": {
      "mc": 4.2,
      "fa": 2.93,
      "bck": 4.12,
      "acb": 4.5,
      "ach": 4.26,
      "bcpb": 3.42,
      "bcph": 3.5,
      "es": 3.29,
      "er": 3.06,
      "ms": 4.75,
      "mr": 4.76,
      "hl": 3.46,
      "eg": 3.45
     },
     "ci": {
      "overall": [
       3.79,
       3.86
      ],
      "groups": {
       "memory": [
        4.05,
        4.35
       ],
       "knowledge": [
        3.41,
        3.63
       ],
       "persona": [
        3.87,
        3.98
       ],
       "emotion": [
        3.1,
        3.25
       ],
       "morality": [
        4.69,
        4.81
       ],
       "believability": [
        3.4,
        3.51
       ]
      }
     },
     "n": 3247
    },
    "en": {
     "overall": 3.82,
     "groups": {
      "memory": 3.9,
      "knowledge": 3.34,
      "persona": 4.1,
      "emotion": 3.17,
      "morality": 4.8,
      "believability": 3.35
     },
     "dims": {
      "mc": 3.9,
      "fa": 2.62,
      "bck": 4.06,
      "acb": 4.67,
      "ach": 4.29,
      "bcpb": 3.74,
      "bcph": 3.68,
      "es": 3.31,
      "er": 3.04,
      "ms": 4.84,
      "mr": 4.76,
      "hl": 3.31,
      "eg": 3.39
     },
     "ci": {
      "overall": [
       3.78,
       3.85
      ],
      "groups": {
       "memory": [
        3.74,
        4.06
       ],
       "knowledge": [
        3.23,
        3.44
       ],
       "persona": [
        4.04,
        4.15
       ],
       "emotion": [
        3.09,
        3.25
       ],
       "morality": [
        4.74,
        4.86
       ],
       "believability": [
        3.29,
        3.4
       ]
      }
     },
     "n": 3247
    }
   },
   "excludedSessions": 0,
   "sessions": {
    "done": 6494,
    "total": 6494
   },
   "eligibility": {
    "eligible": true,
    "fullProtocol": true,
    "complete": true,
    "currentVersion": true,
    "pinned": true,
    "singleHost": true,
    "reason": null
   }
  },
  "judged_samples": 6494
 }
]