{
 "paper_row": "GPT-4o",
 "paper": {
  "zh": {
   "avg": 3.68,
   "mc": 3.98,
   "fa": 2.74,
   "bck": 3.73,
   "acb": 4.46,
   "ach": 4.18,
   "bcpb": 3.33,
   "bcph": 3.35,
   "es": 3.08,
   "er": 2.95,
   "ms": 4.77,
   "mr": 4.72,
   "hl": 3.17,
   "eg": 3.43
  },
  "en": {
   "avg": 3.72,
   "mc": 3.92,
   "fa": 2.66,
   "bck": 4.0,
   "acb": 4.55,
   "ach": 4.04,
   "bcpb": 3.53,
   "bcph": 3.42,
   "es": 3.02,
   "er": 2.97,
   "ms": 4.77,
   "mr": 4.71,
   "hl": 3.34,
   "eg": 3.51
  }
 },
 "runs": [
  {
   "id": "31a478305c1641a6",
   "model": "openai/gpt-4o-2024-05-13",
   "config": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "azure"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "perLang": {
    "zh": {
     "avg": 3.72,
     "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
    },
    "en": {
     "avg": 3.84,
     "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
    }
   },
   "excluded": 34
  },
  {
   "id": "eebe847ae59b4d41",
   "model": "openai/gpt-4o-2024-05-13",
   "config": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 1024,
    "extra": {
     "provider": {
      "only": [
       "azure"
      ],
      "allow_fallbacks": false
     }
    }
   },
   "perLang": {
    "zh": {
     "avg": 3.73,
     "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
    },
    "en": {
     "avg": 3.84,
     "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
    }
   },
   "excluded": 32
  }
 ],
 "compare": {
  "zh": {
   "avg": {
    "paper": 3.68,
    "runs": [
     3.72,
     3.73
    ],
    "mean": 3.725,
    "diff": 0.045,
    "repeat_range": 0.01
   },
   "mc": {
    "paper": 3.98,
    "runs": [
     3.86,
     3.93
    ],
    "mean": 3.895,
    "diff": -0.085,
    "repeat_range": 0.07
   },
   "fa": {
    "paper": 2.74,
    "runs": [
     2.76,
     2.89
    ],
    "mean": 2.825,
    "diff": 0.085,
    "repeat_range": 0.13
   },
   "bck": {
    "paper": 3.73,
    "runs": [
     3.83,
     3.86
    ],
    "mean": 3.845,
    "diff": 0.115,
    "repeat_range": 0.03
   },
   "acb": {
    "paper": 4.46,
    "runs": [
     4.54,
     4.59
    ],
    "mean": 4.565,
    "diff": 0.105,
    "repeat_range": 0.05
   },
   "ach": {
    "paper": 4.18,
    "runs": [
     4.24,
     4.14
    ],
    "mean": 4.19,
    "diff": 0.01,
    "repeat_range": 0.1
   },
   "bcpb": {
    "paper": 3.33,
    "runs": [
     3.47,
     3.45
    ],
    "mean": 3.46,
    "diff": 0.13,
    "repeat_range": 0.02
   },
   "bcph": {
    "paper": 3.35,
    "runs": [
     3.61,
     3.59
    ],
    "mean": 3.6,
    "diff": 0.25,
    "repeat_range": 0.02
   },
   "es": {
    "paper": 3.08,
    "runs": [
     3.19,
     3.22
    ],
    "mean": 3.205,
    "diff": 0.125,
    "repeat_range": 0.03
   },
   "er": {
    "paper": 2.95,
    "runs": [
     3.03,
     3.05
    ],
    "mean": 3.04,
    "diff": 0.09,
    "repeat_range": 0.02
   },
   "ms": {
    "paper": 4.77,
    "runs": [
     4.86,
     4.79
    ],
    "mean": 4.825,
    "diff": 0.055,
    "repeat_range": 0.07
   },
   "mr": {
    "paper": 4.72,
    "runs": [
     4.79,
     4.8
    ],
    "mean": 4.795,
    "diff": 0.075,
    "repeat_range": 0.01
   },
   "hl": {
    "paper": 3.17,
    "runs": [
     3.04,
     3.04
    ],
    "mean": 3.04,
    "diff": -0.13,
    "repeat_range": 0.0
   },
   "eg": {
    "paper": 3.43,
    "runs": [
     3.18,
     3.17
    ],
    "mean": 3.175,
    "diff": -0.255,
    "repeat_range": 0.01
   }
  },
  "en": {
   "avg": {
    "paper": 3.72,
    "runs": [
     3.84,
     3.84
    ],
    "mean": 3.84,
    "diff": 0.12,
    "repeat_range": 0.0
   },
   "mc": {
    "paper": 3.92,
    "runs": [
     3.9,
     3.83
    ],
    "mean": 3.865,
    "diff": -0.055,
    "repeat_range": 0.07
   },
   "fa": {
    "paper": 2.66,
    "runs": [
     2.63,
     2.8
    ],
    "mean": 2.715,
    "diff": 0.055,
    "repeat_range": 0.17
   },
   "bck": {
    "paper": 4.0,
    "runs": [
     3.88,
     3.83
    ],
    "mean": 3.855,
    "diff": -0.145,
    "repeat_range": 0.05
   },
   "acb": {
    "paper": 4.55,
    "runs": [
     4.73,
     4.77
    ],
    "mean": 4.75,
    "diff": 0.2,
    "repeat_range": 0.04
   },
   "ach": {
    "paper": 4.04,
    "runs": [
     4.3,
     4.26
    ],
    "mean": 4.28,
    "diff": 0.24,
    "repeat_range": 0.04
   },
   "bcpb": {
    "paper": 3.53,
    "runs": [
     3.99,
     3.96
    ],
    "mean": 3.975,
    "diff": 0.445,
    "repeat_range": 0.03
   },
   "bcph": {
    "paper": 3.42,
    "runs": [
     3.96,
     3.98
    ],
    "mean": 3.97,
    "diff": 0.55,
    "repeat_range": 0.02
   },
   "es": {
    "paper": 3.02,
    "runs": [
     3.31,
     3.23
    ],
    "mean": 3.27,
    "diff": 0.25,
    "repeat_range": 0.08
   },
   "er": {
    "paper": 2.97,
    "runs": [
     3.14,
     3.14
    ],
    "mean": 3.14,
    "diff": 0.17,
    "repeat_range": 0.0
   },
   "ms": {
    "paper": 4.77,
    "runs": [
     4.95,
     4.92
    ],
    "mean": 4.935,
    "diff": 0.165,
    "repeat_range": 0.03
   },
   "mr": {
    "paper": 4.71,
    "runs": [
     4.88,
     4.91
    ],
    "mean": 4.895,
    "diff": 0.185,
    "repeat_range": 0.03
   },
   "hl": {
    "paper": 3.34,
    "runs": [
     3.14,
     3.13
    ],
    "mean": 3.135,
    "diff": -0.205,
    "repeat_range": 0.01
   },
   "eg": {
    "paper": 3.51,
    "runs": [
     3.17,
     3.2
    ],
    "mean": 3.185,
    "diff": -0.325,
    "repeat_range": 0.03
   }
  }
 },
 "judge_bias_correlation": {
  "zh": 0.61,
  "en": 0.57
 }
}