{
  "models": [
    {
      "model_id": "Anthropic-LM-v4-s3-52B",
      "name": "Anthropic-LM v4-s3 52B",
      "developer": "unknown",
      "scores": {
        "Mean win rate": 0.78,
        "MMLU": 0.481,
        "BoolQ": 0.815,
        "NarrativeQA": 0.728,
        "NaturalQuestions (open-book)": 0.686,
        "QuAC": 0.431,
        "HellaSwag": 0.807,
        "OpenbookQA": 0.558,
        "TruthfulQA": 0.368,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.154,
        "XSUM": 0.134,
        "IMDB": 0.934,
        "CivilComments": 0.61,
        "RAFT": 0.699
      }
    },
    {
      "model_id": "EleutherAI/pythia-12b",
      "name": "Pythia 12B",
      "developer": "EleutherAI",
      "scores": {
        "Mean win rate": 0.257,
        "MMLU": 0.274,
        "BoolQ": 0.662,
        "NarrativeQA": 0.596,
        "NaturalQuestions (open-book)": 0.581,
        "QuAC": 0.313,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.177,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.931,
        "CivilComments": 0.531,
        "RAFT": 0.514
      }
    },
    {
      "model_id": "EleutherAI/pythia-6.9b",
      "name": "Pythia 6.9B",
      "developer": "EleutherAI",
      "scores": {
        "Mean win rate": 0.196,
        "MMLU": 0.236,
        "BoolQ": 0.631,
        "NarrativeQA": 0.528,
        "NaturalQuestions (open-book)": 0.539,
        "QuAC": 0.296,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.213,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.928,
        "CivilComments": 0.511,
        "RAFT": 0.502
      }
    },
    {
      "model_id": "ai21/J1-Grande-v1-17B",
      "name": "J1-Grande v1 17B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.433,
        "MMLU": 0.27,
        "BoolQ": 0.722,
        "NarrativeQA": 0.672,
        "NaturalQuestions (open-book)": 0.578,
        "QuAC": 0.362,
        "HellaSwag": 0.739,
        "OpenbookQA": 0.52,
        "TruthfulQA": 0.193,
        "MS MARCO (TREC)": 0.341,
        "CNN/DailyMail": 0.143,
        "XSUM": 0.122,
        "IMDB": 0.953,
        "CivilComments": 0.529,
        "RAFT": 0.658
      }
    },
    {
      "model_id": "ai21/J1-Grande-v2-beta-17B",
      "name": "J1-Grande v2 beta 17B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.706,
        "MMLU": 0.445,
        "BoolQ": 0.812,
        "NarrativeQA": 0.725,
        "NaturalQuestions (open-book)": 0.625,
        "QuAC": 0.392,
        "HellaSwag": 0.764,
        "OpenbookQA": 0.56,
        "TruthfulQA": 0.306,
        "MS MARCO (TREC)": 0.46,
        "CNN/DailyMail": 0.146,
        "XSUM": 0.152,
        "IMDB": 0.957,
        "CivilComments": 0.546,
        "RAFT": 0.679
      }
    },
    {
      "model_id": "ai21/J1-Jumbo-v1-178B",
      "name": "J1-Jumbo v1 178B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.517,
        "MMLU": 0.259,
        "BoolQ": 0.776,
        "NarrativeQA": 0.695,
        "NaturalQuestions (open-book)": 0.595,
        "QuAC": 0.358,
        "HellaSwag": 0.765,
        "OpenbookQA": 0.534,
        "TruthfulQA": 0.175,
        "MS MARCO (TREC)": 0.363,
        "CNN/DailyMail": 0.144,
        "XSUM": 0.129,
        "IMDB": 0.943,
        "CivilComments": 0.553,
        "RAFT": 0.681
      }
    },
    {
      "model_id": "ai21/J1-Large-v1-7.5B",
      "name": "J1-Large v1 7.5B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.285,
        "MMLU": 0.241,
        "BoolQ": 0.683,
        "NarrativeQA": 0.623,
        "NaturalQuestions (open-book)": 0.532,
        "QuAC": 0.328,
        "HellaSwag": 0.7,
        "OpenbookQA": 0.514,
        "TruthfulQA": 0.197,
        "MS MARCO (TREC)": 0.292,
        "CNN/DailyMail": 0.134,
        "XSUM": 0.102,
        "IMDB": 0.956,
        "CivilComments": 0.532,
        "RAFT": 0.545
      }
    },
    {
      "model_id": "ai21/Jurassic-2-Grande-17B",
      "name": "Jurassic-2 Grande 17B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.743,
        "MMLU": 0.475,
        "BoolQ": 0.826,
        "NarrativeQA": 0.737,
        "NaturalQuestions (open-book)": 0.639,
        "QuAC": 0.418,
        "HellaSwag": 0.781,
        "OpenbookQA": 0.542,
        "TruthfulQA": 0.348,
        "MS MARCO (TREC)": 0.514,
        "CNN/DailyMail": 0.144,
        "XSUM": 0.167,
        "IMDB": 0.938,
        "CivilComments": 0.547,
        "RAFT": 0.712
      }
    },
    {
      "model_id": "ai21/Jurassic-2-Jumbo-178B",
      "name": "Jurassic-2 Jumbo 178B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.824,
        "MMLU": 0.48,
        "BoolQ": 0.829,
        "NarrativeQA": 0.733,
        "NaturalQuestions (open-book)": 0.669,
        "QuAC": 0.435,
        "HellaSwag": 0.788,
        "OpenbookQA": 0.558,
        "TruthfulQA": 0.437,
        "MS MARCO (TREC)": 0.661,
        "CNN/DailyMail": 0.149,
        "XSUM": 0.182,
        "IMDB": 0.938,
        "CivilComments": 0.57,
        "RAFT": 0.746
      }
    },
    {
      "model_id": "ai21/Jurassic-2-Large-7.5B",
      "name": "Jurassic-2 Large 7.5B",
      "developer": "ai21",
      "scores": {
        "Mean win rate": 0.553,
        "MMLU": 0.339,
        "BoolQ": 0.742,
        "NarrativeQA": -1.0,
        "NaturalQuestions (open-book)": 0.589,
        "QuAC": -1.0,
        "HellaSwag": 0.729,
        "OpenbookQA": 0.53,
        "TruthfulQA": 0.245,
        "MS MARCO (TREC)": 0.464,
        "CNN/DailyMail": 0.136,
        "XSUM": 0.142,
        "IMDB": 0.956,
        "CivilComments": 0.57,
        "RAFT": 0.622
      }
    },
    {
      "model_id": "aleph-alpha/Luminous-Base-13B",
      "name": "Luminous Base 13B",
      "developer": "aleph-alpha",
      "scores": {
        "Mean win rate": 0.315,
        "MMLU": 0.27,
        "BoolQ": 0.719,
        "NarrativeQA": 0.605,
        "NaturalQuestions (open-book)": 0.568,
        "QuAC": 0.334,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.182,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.11,
        "XSUM": 0.105,
        "IMDB": 0.939,
        "CivilComments": 0.544,
        "RAFT": 0.473
      }
    },
    {
      "model_id": "aleph-alpha/Luminous-Extended-30B",
      "name": "Luminous Extended 30B",
      "developer": "aleph-alpha",
      "scores": {
        "Mean win rate": 0.485,
        "MMLU": 0.321,
        "BoolQ": 0.767,
        "NarrativeQA": 0.665,
        "NaturalQuestions (open-book)": 0.609,
        "QuAC": 0.349,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.221,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.139,
        "XSUM": 0.124,
        "IMDB": 0.947,
        "CivilComments": 0.524,
        "RAFT": 0.523
      }
    },
    {
      "model_id": "aleph-alpha/Luminous-Supreme-70B",
      "name": "Luminous Supreme 70B",
      "developer": "aleph-alpha",
      "scores": {
        "Mean win rate": 0.662,
        "MMLU": 0.38,
        "BoolQ": 0.775,
        "NarrativeQA": 0.711,
        "NaturalQuestions (open-book)": 0.649,
        "QuAC": 0.37,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.222,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.15,
        "XSUM": 0.136,
        "IMDB": 0.959,
        "CivilComments": 0.562,
        "RAFT": 0.653
      }
    },
    {
      "model_id": "bigscience/BLOOM-176B",
      "name": "BLOOM 176B",
      "developer": "bigscience",
      "scores": {
        "Mean win rate": 0.446,
        "MMLU": 0.299,
        "BoolQ": 0.704,
        "NarrativeQA": 0.662,
        "NaturalQuestions (open-book)": 0.621,
        "QuAC": 0.361,
        "HellaSwag": 0.744,
        "OpenbookQA": 0.534,
        "TruthfulQA": 0.205,
        "MS MARCO (TREC)": 0.386,
        "CNN/DailyMail": 0.08,
        "XSUM": 0.03,
        "IMDB": 0.945,
        "CivilComments": 0.62,
        "RAFT": 0.592
      }
    },
    {
      "model_id": "bigscience/T0pp-11B",
      "name": "T0pp 11B",
      "developer": "bigscience",
      "scores": {
        "Mean win rate": 0.197,
        "MMLU": 0.407,
        "BoolQ": 0.0,
        "NarrativeQA": 0.151,
        "NaturalQuestions (open-book)": 0.19,
        "QuAC": 0.121,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.377,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.122,
        "XSUM": 0.09,
        "IMDB": 0.207,
        "CivilComments": 0.234,
        "RAFT": 0.118
      }
    },
    {
      "model_id": "cohere/Cohere-Command-beta-52.4B",
      "name": "Cohere Command beta 52.4B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.874,
        "MMLU": 0.452,
        "BoolQ": 0.856,
        "NarrativeQA": 0.752,
        "NaturalQuestions (open-book)": 0.76,
        "QuAC": 0.432,
        "HellaSwag": 0.811,
        "OpenbookQA": 0.582,
        "TruthfulQA": 0.269,
        "MS MARCO (TREC)": 0.762,
        "CNN/DailyMail": 0.161,
        "XSUM": 0.152,
        "IMDB": 0.96,
        "CivilComments": 0.601,
        "RAFT": 0.667
      }
    },
    {
      "model_id": "cohere/Cohere-Command-beta-6.1B",
      "name": "Cohere Command beta 6.1B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.675,
        "MMLU": 0.406,
        "BoolQ": 0.798,
        "NarrativeQA": 0.709,
        "NaturalQuestions (open-book)": 0.717,
        "QuAC": 0.375,
        "HellaSwag": 0.752,
        "OpenbookQA": 0.55,
        "TruthfulQA": 0.203,
        "MS MARCO (TREC)": 0.709,
        "CNN/DailyMail": 0.153,
        "XSUM": 0.122,
        "IMDB": 0.961,
        "CivilComments": 0.54,
        "RAFT": 0.634
      }
    },
    {
      "model_id": "cohere/Cohere-large-v20220720-13.1B",
      "name": "Cohere large v20220720 13.1B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.372,
        "MMLU": 0.324,
        "BoolQ": 0.725,
        "NarrativeQA": 0.625,
        "NaturalQuestions (open-book)": 0.573,
        "QuAC": 0.338,
        "HellaSwag": 0.736,
        "OpenbookQA": 0.542,
        "TruthfulQA": 0.181,
        "MS MARCO (TREC)": 0.33,
        "CNN/DailyMail": 0.126,
        "XSUM": 0.108,
        "IMDB": 0.933,
        "CivilComments": 0.507,
        "RAFT": 0.596
      }
    },
    {
      "model_id": "cohere/Cohere-medium-v20220720-6.1B",
      "name": "Cohere medium v20220720 6.1B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.23,
        "MMLU": 0.279,
        "BoolQ": 0.659,
        "NarrativeQA": 0.559,
        "NaturalQuestions (open-book)": 0.504,
        "QuAC": 0.279,
        "HellaSwag": 0.706,
        "OpenbookQA": 0.496,
        "TruthfulQA": 0.19,
        "MS MARCO (TREC)": 0.374,
        "CNN/DailyMail": 0.077,
        "XSUM": 0.087,
        "IMDB": 0.935,
        "CivilComments": 0.504,
        "RAFT": 0.52
      }
    },
    {
      "model_id": "cohere/Cohere-medium-v20221108-6.1B",
      "name": "Cohere medium v20221108 6.1B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.312,
        "MMLU": 0.254,
        "BoolQ": 0.7,
        "NarrativeQA": 0.61,
        "NaturalQuestions (open-book)": 0.517,
        "QuAC": 0.314,
        "HellaSwag": 0.726,
        "OpenbookQA": 0.538,
        "TruthfulQA": 0.215,
        "MS MARCO (TREC)": 0.373,
        "CNN/DailyMail": 0.121,
        "XSUM": 0.099,
        "IMDB": 0.935,
        "CivilComments": 0.5,
        "RAFT": 0.591
      }
    },
    {
      "model_id": "cohere/Cohere-small-v20220720-410M",
      "name": "Cohere small v20220720 410M",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.109,
        "MMLU": 0.264,
        "BoolQ": 0.457,
        "NarrativeQA": 0.294,
        "NaturalQuestions (open-book)": 0.309,
        "QuAC": 0.219,
        "HellaSwag": 0.483,
        "OpenbookQA": 0.348,
        "TruthfulQA": 0.217,
        "MS MARCO (TREC)": 0.304,
        "CNN/DailyMail": 0.063,
        "XSUM": 0.033,
        "IMDB": 0.578,
        "CivilComments": 0.501,
        "RAFT": 0.492
      }
    },
    {
      "model_id": "cohere/Cohere-xlarge-v20220609-52.4B",
      "name": "Cohere xlarge v20220609 52.4B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.56,
        "MMLU": 0.353,
        "BoolQ": 0.718,
        "NarrativeQA": 0.65,
        "NaturalQuestions (open-book)": 0.595,
        "QuAC": 0.361,
        "HellaSwag": 0.811,
        "OpenbookQA": 0.55,
        "TruthfulQA": 0.198,
        "MS MARCO (TREC)": 0.459,
        "CNN/DailyMail": 0.144,
        "XSUM": 0.129,
        "IMDB": 0.956,
        "CivilComments": 0.532,
        "RAFT": 0.633
      }
    },
    {
      "model_id": "cohere/Cohere-xlarge-v20221108-52.4B",
      "name": "Cohere xlarge v20221108 52.4B",
      "developer": "cohere",
      "scores": {
        "Mean win rate": 0.664,
        "MMLU": 0.382,
        "BoolQ": 0.762,
        "NarrativeQA": 0.672,
        "NaturalQuestions (open-book)": 0.628,
        "QuAC": 0.374,
        "HellaSwag": 0.81,
        "OpenbookQA": 0.588,
        "TruthfulQA": 0.169,
        "MS MARCO (TREC)": 0.55,
        "CNN/DailyMail": 0.153,
        "XSUM": 0.153,
        "IMDB": 0.956,
        "CivilComments": 0.524,
        "RAFT": 0.624
      }
    },
    {
      "model_id": "google/Palmyra-X-43B",
      "name": "Palmyra X 43B",
      "developer": "Google",
      "scores": {
        "Mean win rate": 0.732,
        "MMLU": 0.609,
        "BoolQ": 0.896,
        "NarrativeQA": 0.742,
        "NaturalQuestions (open-book)": -1.0,
        "QuAC": 0.473,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.616,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.049,
        "XSUM": 0.149,
        "IMDB": 0.935,
        "CivilComments": 0.008,
        "RAFT": 0.701
      }
    },
    {
      "model_id": "google/T5-11B",
      "name": "T5 11B",
      "developer": "Google",
      "scores": {
        "Mean win rate": 0.131,
        "MMLU": 0.29,
        "BoolQ": 0.761,
        "NarrativeQA": 0.086,
        "NaturalQuestions (open-book)": 0.477,
        "QuAC": 0.116,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.133,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.043,
        "XSUM": 0.015,
        "IMDB": 0.379,
        "CivilComments": 0.509,
        "RAFT": 0.37
      }
    },
    {
      "model_id": "google/UL2-20B",
      "name": "UL2 20B",
      "developer": "Google",
      "scores": {
        "Mean win rate": 0.167,
        "MMLU": 0.291,
        "BoolQ": 0.746,
        "NarrativeQA": 0.083,
        "NaturalQuestions (open-book)": 0.349,
        "QuAC": 0.144,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.193,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.03,
        "XSUM": 0.058,
        "IMDB": 0.337,
        "CivilComments": 0.521,
        "RAFT": 0.404
      }
    },
    {
      "model_id": "lmsys/Vicuna-v1.3-13B",
      "name": "Vicuna v1.3 13B",
      "developer": "lmsys",
      "scores": {
        "Mean win rate": 0.706,
        "MMLU": 0.462,
        "BoolQ": 0.808,
        "NarrativeQA": 0.691,
        "NaturalQuestions (open-book)": 0.686,
        "QuAC": 0.403,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.385,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.762,
        "CivilComments": 0.645,
        "RAFT": 0.657
      }
    },
    {
      "model_id": "lmsys/Vicuna-v1.3-7B",
      "name": "Vicuna v1.3 7B",
      "developer": "lmsys",
      "scores": {
        "Mean win rate": 0.625,
        "MMLU": 0.434,
        "BoolQ": 0.76,
        "NarrativeQA": 0.643,
        "NaturalQuestions (open-book)": 0.634,
        "QuAC": 0.392,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.292,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.916,
        "CivilComments": 0.62,
        "RAFT": 0.693
      }
    },
    {
      "model_id": "meta/LLaMA-13B",
      "name": "LLaMA 13B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.595,
        "MMLU": 0.422,
        "BoolQ": 0.714,
        "NarrativeQA": 0.711,
        "NaturalQuestions (open-book)": 0.614,
        "QuAC": 0.347,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.324,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.928,
        "CivilComments": 0.6,
        "RAFT": 0.643
      }
    },
    {
      "model_id": "meta/LLaMA-30B",
      "name": "LLaMA 30B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.781,
        "MMLU": 0.531,
        "BoolQ": 0.861,
        "NarrativeQA": 0.752,
        "NaturalQuestions (open-book)": 0.666,
        "QuAC": 0.39,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.344,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.927,
        "CivilComments": 0.549,
        "RAFT": 0.752
      }
    },
    {
      "model_id": "meta/LLaMA-65B",
      "name": "LLaMA 65B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.908,
        "MMLU": 0.584,
        "BoolQ": 0.871,
        "NarrativeQA": 0.755,
        "NaturalQuestions (open-book)": 0.672,
        "QuAC": 0.401,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.508,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.962,
        "CivilComments": 0.655,
        "RAFT": 0.702
      }
    },
    {
      "model_id": "meta/LLaMA-7B",
      "name": "LLaMA 7B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.533,
        "MMLU": 0.321,
        "BoolQ": 0.756,
        "NarrativeQA": 0.669,
        "NaturalQuestions (open-book)": 0.589,
        "QuAC": 0.338,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.28,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.947,
        "CivilComments": 0.563,
        "RAFT": 0.573
      }
    },
    {
      "model_id": "meta/OPT-175B",
      "name": "OPT 175B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.609,
        "MMLU": 0.318,
        "BoolQ": 0.793,
        "NarrativeQA": 0.671,
        "NaturalQuestions (open-book)": 0.615,
        "QuAC": 0.36,
        "HellaSwag": 0.791,
        "OpenbookQA": 0.586,
        "TruthfulQA": 0.25,
        "MS MARCO (TREC)": 0.448,
        "CNN/DailyMail": 0.146,
        "XSUM": 0.155,
        "IMDB": 0.947,
        "CivilComments": 0.505,
        "RAFT": 0.606
      }
    },
    {
      "model_id": "meta/OPT-66B",
      "name": "OPT 66B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.448,
        "MMLU": 0.276,
        "BoolQ": 0.76,
        "NarrativeQA": 0.638,
        "NaturalQuestions (open-book)": 0.596,
        "QuAC": 0.357,
        "HellaSwag": 0.745,
        "OpenbookQA": 0.534,
        "TruthfulQA": 0.201,
        "MS MARCO (TREC)": 0.482,
        "CNN/DailyMail": 0.136,
        "XSUM": 0.126,
        "IMDB": 0.917,
        "CivilComments": 0.506,
        "RAFT": 0.557
      }
    },
    {
      "model_id": "meta/llama-2-13b",
      "name": "Llama 2 13B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.823,
        "MMLU": 0.507,
        "BoolQ": 0.811,
        "NarrativeQA": 0.744,
        "NaturalQuestions (open-book)": 0.637,
        "QuAC": 0.424,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.33,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.962,
        "CivilComments": 0.588,
        "RAFT": 0.707
      }
    },
    {
      "model_id": "meta/llama-2-70b",
      "name": "Llama 2 70B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.944,
        "MMLU": 0.582,
        "BoolQ": 0.886,
        "NarrativeQA": 0.77,
        "NaturalQuestions (open-book)": 0.674,
        "QuAC": 0.484,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.554,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.961,
        "CivilComments": 0.652,
        "RAFT": 0.727
      }
    },
    {
      "model_id": "meta/llama-2-7b",
      "name": "Llama 2 7B",
      "developer": "Meta",
      "scores": {
        "Mean win rate": 0.607,
        "MMLU": 0.431,
        "BoolQ": 0.762,
        "NarrativeQA": 0.691,
        "NaturalQuestions (open-book)": 0.611,
        "QuAC": 0.406,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.272,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.907,
        "CivilComments": 0.562,
        "RAFT": 0.643
      }
    },
    {
      "model_id": "microsoft/TNLG-v2-530B",
      "name": "TNLG v2 530B",
      "developer": "microsoft",
      "scores": {
        "Mean win rate": 0.787,
        "MMLU": 0.469,
        "BoolQ": 0.809,
        "NarrativeQA": 0.722,
        "NaturalQuestions (open-book)": 0.642,
        "QuAC": 0.39,
        "HellaSwag": 0.799,
        "OpenbookQA": 0.562,
        "TruthfulQA": 0.251,
        "MS MARCO (TREC)": 0.643,
        "CNN/DailyMail": 0.161,
        "XSUM": 0.169,
        "IMDB": 0.941,
        "CivilComments": 0.601,
        "RAFT": 0.679
      }
    },
    {
      "model_id": "microsoft/TNLG-v2-6.7B",
      "name": "TNLG v2 6.7B",
      "developer": "microsoft",
      "scores": {
        "Mean win rate": 0.309,
        "MMLU": 0.242,
        "BoolQ": 0.698,
        "NarrativeQA": 0.631,
        "NaturalQuestions (open-book)": 0.561,
        "QuAC": 0.345,
        "HellaSwag": 0.704,
        "OpenbookQA": 0.478,
        "TruthfulQA": 0.167,
        "MS MARCO (TREC)": 0.332,
        "CNN/DailyMail": 0.146,
        "XSUM": 0.11,
        "IMDB": 0.927,
        "CivilComments": 0.532,
        "RAFT": 0.525
      }
    },
    {
      "model_id": "mistralai/Mistral-v0.1-7B",
      "name": "Mistral v0.1 7B",
      "developer": "mistralai",
      "scores": {
        "Mean win rate": 0.884,
        "MMLU": 0.572,
        "BoolQ": 0.874,
        "NarrativeQA": 0.716,
        "NaturalQuestions (open-book)": 0.687,
        "QuAC": 0.423,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.422,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.962,
        "CivilComments": 0.624,
        "RAFT": 0.707
      }
    },
    {
      "model_id": "mosaicml/MPT-30B",
      "name": "MPT 30B",
      "developer": "mosaicml",
      "scores": {
        "Mean win rate": 0.714,
        "MMLU": 0.437,
        "BoolQ": 0.704,
        "NarrativeQA": 0.732,
        "NaturalQuestions (open-book)": 0.673,
        "QuAC": 0.393,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.231,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.959,
        "CivilComments": 0.599,
        "RAFT": 0.723
      }
    },
    {
      "model_id": "mosaicml/MPT-Instruct-30B",
      "name": "MPT-Instruct 30B",
      "developer": "mosaicml",
      "scores": {
        "Mean win rate": 0.716,
        "MMLU": 0.444,
        "BoolQ": 0.85,
        "NarrativeQA": 0.733,
        "NaturalQuestions (open-book)": 0.697,
        "QuAC": 0.327,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.234,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.956,
        "CivilComments": 0.573,
        "RAFT": 0.68
      }
    },
    {
      "model_id": "openai/GPT-J-6B",
      "name": "GPT-J 6B",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.273,
        "MMLU": 0.249,
        "BoolQ": 0.649,
        "NarrativeQA": 0.545,
        "NaturalQuestions (open-book)": 0.559,
        "QuAC": 0.33,
        "HellaSwag": 0.663,
        "OpenbookQA": 0.514,
        "TruthfulQA": 0.199,
        "MS MARCO (TREC)": 0.345,
        "CNN/DailyMail": 0.131,
        "XSUM": 0.096,
        "IMDB": 0.939,
        "CivilComments": 0.52,
        "RAFT": 0.619
      }
    },
    {
      "model_id": "openai/GPT-NeoX-20B",
      "name": "GPT-NeoX 20B",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.351,
        "MMLU": 0.276,
        "BoolQ": 0.683,
        "NarrativeQA": 0.599,
        "NaturalQuestions (open-book)": 0.596,
        "QuAC": 0.326,
        "HellaSwag": 0.718,
        "OpenbookQA": 0.524,
        "TruthfulQA": 0.216,
        "MS MARCO (TREC)": 0.398,
        "CNN/DailyMail": 0.123,
        "XSUM": 0.102,
        "IMDB": 0.948,
        "CivilComments": 0.516,
        "RAFT": 0.505
      }
    },
    {
      "model_id": "openai/ada-350M",
      "name": "ada 350M",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.108,
        "MMLU": 0.243,
        "BoolQ": 0.581,
        "NarrativeQA": 0.326,
        "NaturalQuestions (open-book)": 0.365,
        "QuAC": 0.242,
        "HellaSwag": 0.435,
        "OpenbookQA": 0.38,
        "TruthfulQA": 0.215,
        "MS MARCO (TREC)": 0.29,
        "CNN/DailyMail": 0.09,
        "XSUM": 0.022,
        "IMDB": 0.849,
        "CivilComments": 0.517,
        "RAFT": 0.423
      }
    },
    {
      "model_id": "openai/babbage-1.3B",
      "name": "babbage 1.3B",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.114,
        "MMLU": 0.235,
        "BoolQ": 0.574,
        "NarrativeQA": 0.491,
        "NaturalQuestions (open-book)": 0.451,
        "QuAC": 0.273,
        "HellaSwag": 0.555,
        "OpenbookQA": 0.438,
        "TruthfulQA": 0.188,
        "MS MARCO (TREC)": 0.317,
        "CNN/DailyMail": 0.079,
        "XSUM": 0.045,
        "IMDB": 0.597,
        "CivilComments": 0.519,
        "RAFT": 0.455
      }
    },
    {
      "model_id": "openai/curie-6.7B",
      "name": "curie 6.7B",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.247,
        "MMLU": 0.243,
        "BoolQ": 0.656,
        "NarrativeQA": 0.604,
        "NaturalQuestions (open-book)": 0.552,
        "QuAC": 0.321,
        "HellaSwag": 0.682,
        "OpenbookQA": 0.502,
        "TruthfulQA": 0.232,
        "MS MARCO (TREC)": 0.3,
        "CNN/DailyMail": 0.113,
        "XSUM": 0.091,
        "IMDB": 0.889,
        "CivilComments": 0.539,
        "RAFT": 0.49
      }
    },
    {
      "model_id": "openai/davinci-175B",
      "name": "davinci 175B",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.538,
        "MMLU": 0.422,
        "BoolQ": 0.722,
        "NarrativeQA": 0.687,
        "NaturalQuestions (open-book)": 0.625,
        "QuAC": 0.36,
        "HellaSwag": 0.775,
        "OpenbookQA": 0.586,
        "TruthfulQA": 0.194,
        "MS MARCO (TREC)": 0.378,
        "CNN/DailyMail": 0.127,
        "XSUM": 0.126,
        "IMDB": 0.933,
        "CivilComments": 0.532,
        "RAFT": 0.642
      }
    },
    {
      "model_id": "openai/gpt-3.5-turbo-0301",
      "name": "gpt-3.5-turbo-0301",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.76,
        "MMLU": 0.59,
        "BoolQ": 0.74,
        "NarrativeQA": 0.663,
        "NaturalQuestions (open-book)": 0.624,
        "QuAC": 0.512,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.609,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.899,
        "CivilComments": 0.674,
        "RAFT": 0.768
      }
    },
    {
      "model_id": "openai/gpt-3.5-turbo-0613",
      "name": "GPT-3.5 Turbo 0613",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.783,
        "MMLU": 0.391,
        "BoolQ": 0.87,
        "NarrativeQA": 0.625,
        "NaturalQuestions (open-book)": 0.675,
        "QuAC": 0.485,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.339,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.943,
        "CivilComments": 0.696,
        "RAFT": 0.748
      }
    },
    {
      "model_id": "openai/text-ada-001",
      "name": "text-ada-001",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.107,
        "MMLU": 0.238,
        "BoolQ": 0.464,
        "NarrativeQA": 0.238,
        "NaturalQuestions (open-book)": 0.149,
        "QuAC": 0.176,
        "HellaSwag": 0.429,
        "OpenbookQA": 0.346,
        "TruthfulQA": 0.232,
        "MS MARCO (TREC)": 0.302,
        "CNN/DailyMail": 0.136,
        "XSUM": 0.034,
        "IMDB": 0.822,
        "CivilComments": 0.503,
        "RAFT": 0.406
      }
    },
    {
      "model_id": "openai/text-babbage-001",
      "name": "text-babbage-001",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.229,
        "MMLU": 0.229,
        "BoolQ": 0.451,
        "NarrativeQA": 0.429,
        "NaturalQuestions (open-book)": 0.33,
        "QuAC": 0.284,
        "HellaSwag": 0.561,
        "OpenbookQA": 0.452,
        "TruthfulQA": 0.233,
        "MS MARCO (TREC)": 0.449,
        "CNN/DailyMail": 0.151,
        "XSUM": 0.046,
        "IMDB": 0.913,
        "CivilComments": 0.499,
        "RAFT": 0.509
      }
    },
    {
      "model_id": "openai/text-curie-001",
      "name": "text-curie-001",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.36,
        "MMLU": 0.237,
        "BoolQ": 0.62,
        "NarrativeQA": 0.582,
        "NaturalQuestions (open-book)": 0.571,
        "QuAC": 0.358,
        "HellaSwag": 0.676,
        "OpenbookQA": 0.514,
        "TruthfulQA": 0.257,
        "MS MARCO (TREC)": 0.507,
        "CNN/DailyMail": 0.152,
        "XSUM": 0.076,
        "IMDB": 0.923,
        "CivilComments": 0.537,
        "RAFT": 0.489
      }
    },
    {
      "model_id": "openai/text-davinci-002",
      "name": "GPT-3.5 text-davinci-002",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.905,
        "MMLU": 0.568,
        "BoolQ": 0.877,
        "NarrativeQA": 0.727,
        "NaturalQuestions (open-book)": 0.713,
        "QuAC": 0.445,
        "HellaSwag": 0.815,
        "OpenbookQA": 0.594,
        "TruthfulQA": 0.61,
        "MS MARCO (TREC)": 0.664,
        "CNN/DailyMail": 0.153,
        "XSUM": 0.144,
        "IMDB": 0.948,
        "CivilComments": 0.668,
        "RAFT": 0.733
      }
    },
    {
      "model_id": "openai/text-davinci-003",
      "name": "GPT-3.5 text-davinci-003",
      "developer": "OpenAI",
      "scores": {
        "Mean win rate": 0.872,
        "MMLU": 0.569,
        "BoolQ": 0.881,
        "NarrativeQA": 0.727,
        "NaturalQuestions (open-book)": 0.77,
        "QuAC": 0.525,
        "HellaSwag": 0.822,
        "OpenbookQA": 0.646,
        "TruthfulQA": 0.593,
        "MS MARCO (TREC)": 0.644,
        "CNN/DailyMail": 0.156,
        "XSUM": 0.124,
        "IMDB": 0.848,
        "CivilComments": 0.684,
        "RAFT": 0.759
      }
    },
    {
      "model_id": "stanford/Alpaca-7B",
      "name": "Alpaca 7B",
      "developer": "stanford",
      "scores": {
        "Mean win rate": 0.381,
        "MMLU": 0.385,
        "BoolQ": 0.778,
        "NarrativeQA": 0.396,
        "NaturalQuestions (open-book)": 0.592,
        "QuAC": 0.27,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.243,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.738,
        "CivilComments": 0.566,
        "RAFT": 0.486
      }
    },
    {
      "model_id": "tiiuae/Falcon-Instruct-40B",
      "name": "Falcon-Instruct 40B",
      "developer": "tiiuae",
      "scores": {
        "Mean win rate": 0.727,
        "MMLU": 0.497,
        "BoolQ": 0.829,
        "NarrativeQA": 0.625,
        "NaturalQuestions (open-book)": 0.666,
        "QuAC": 0.371,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.384,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.959,
        "CivilComments": 0.603,
        "RAFT": 0.586
      }
    },
    {
      "model_id": "tiiuae/Falcon-Instruct-7B",
      "name": "Falcon-Instruct 7B",
      "developer": "tiiuae",
      "scores": {
        "Mean win rate": 0.244,
        "MMLU": 0.275,
        "BoolQ": 0.72,
        "NarrativeQA": 0.476,
        "NaturalQuestions (open-book)": 0.449,
        "QuAC": 0.311,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.213,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.852,
        "CivilComments": 0.511,
        "RAFT": 0.523
      }
    },
    {
      "model_id": "tiiuae/falcon-40b",
      "name": "Falcon 40B",
      "developer": "tiiuae",
      "scores": {
        "Mean win rate": 0.729,
        "MMLU": 0.509,
        "BoolQ": 0.819,
        "NarrativeQA": 0.673,
        "NaturalQuestions (open-book)": 0.675,
        "QuAC": 0.307,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.353,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.959,
        "CivilComments": 0.552,
        "RAFT": 0.661
      }
    },
    {
      "model_id": "tiiuae/falcon-7b",
      "name": "Falcon 7B",
      "developer": "tiiuae",
      "scores": {
        "Mean win rate": 0.378,
        "MMLU": 0.286,
        "BoolQ": 0.753,
        "NarrativeQA": 0.621,
        "NaturalQuestions (open-book)": 0.579,
        "QuAC": 0.332,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.234,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.836,
        "CivilComments": 0.514,
        "RAFT": 0.602
      }
    },
    {
      "model_id": "together/RedPajama-INCITE-Base-7B",
      "name": "RedPajama-INCITE-Base 7B",
      "developer": "together",
      "scores": {
        "Mean win rate": 0.378,
        "MMLU": 0.302,
        "BoolQ": 0.713,
        "NarrativeQA": 0.617,
        "NaturalQuestions (open-book)": 0.586,
        "QuAC": 0.336,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.205,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.752,
        "CivilComments": 0.547,
        "RAFT": 0.648
      }
    },
    {
      "model_id": "together/RedPajama-INCITE-Base-v1-3B",
      "name": "RedPajama-INCITE-Base-v1 3B",
      "developer": "together",
      "scores": {
        "Mean win rate": 0.311,
        "MMLU": 0.263,
        "BoolQ": 0.685,
        "NarrativeQA": 0.555,
        "NaturalQuestions (open-book)": 0.52,
        "QuAC": 0.309,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.277,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.907,
        "CivilComments": 0.549,
        "RAFT": 0.502
      }
    },
    {
      "model_id": "together/RedPajama-INCITE-Instruct-7B",
      "name": "RedPajama-INCITE-Instruct 7B",
      "developer": "together",
      "scores": {
        "Mean win rate": 0.524,
        "MMLU": 0.363,
        "BoolQ": 0.705,
        "NarrativeQA": 0.638,
        "NaturalQuestions (open-book)": 0.659,
        "QuAC": 0.26,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.243,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.927,
        "CivilComments": 0.664,
        "RAFT": 0.695
      }
    },
    {
      "model_id": "together/RedPajama-INCITE-Instruct-v1-3B",
      "name": "RedPajama-INCITE-Instruct-v1 3B",
      "developer": "together",
      "scores": {
        "Mean win rate": 0.366,
        "MMLU": 0.257,
        "BoolQ": 0.677,
        "NarrativeQA": 0.638,
        "NaturalQuestions (open-book)": 0.637,
        "QuAC": 0.259,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.208,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": -1.0,
        "XSUM": -1.0,
        "IMDB": 0.894,
        "CivilComments": 0.549,
        "RAFT": 0.661
      }
    },
    {
      "model_id": "writer/InstructPalmyra-30B",
      "name": "InstructPalmyra 30B",
      "developer": "writer",
      "scores": {
        "Mean win rate": 0.568,
        "MMLU": 0.403,
        "BoolQ": 0.751,
        "NarrativeQA": 0.496,
        "NaturalQuestions (open-book)": 0.682,
        "QuAC": 0.433,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.185,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.152,
        "XSUM": 0.104,
        "IMDB": 0.94,
        "CivilComments": 0.555,
        "RAFT": 0.652
      }
    },
    {
      "model_id": "yandex/YaLM-100B",
      "name": "YaLM 100B",
      "developer": "yandex",
      "scores": {
        "Mean win rate": 0.075,
        "MMLU": 0.243,
        "BoolQ": 0.634,
        "NarrativeQA": 0.252,
        "NaturalQuestions (open-book)": 0.227,
        "QuAC": 0.162,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.202,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.017,
        "XSUM": 0.021,
        "IMDB": 0.836,
        "CivilComments": 0.49,
        "RAFT": 0.395
      }
    },
    {
      "model_id": "zhipu-ai/GLM-130B",
      "name": "GLM 130B",
      "developer": "zhipu-ai",
      "scores": {
        "Mean win rate": 0.512,
        "MMLU": 0.344,
        "BoolQ": 0.784,
        "NarrativeQA": 0.706,
        "NaturalQuestions (open-book)": 0.642,
        "QuAC": 0.272,
        "HellaSwag": -1.0,
        "OpenbookQA": -1.0,
        "TruthfulQA": 0.218,
        "MS MARCO (TREC)": -1.0,
        "CNN/DailyMail": 0.154,
        "XSUM": 0.132,
        "IMDB": 0.955,
        "CivilComments": 0.5,
        "RAFT": 0.598
      }
    }
  ]
}