{
  "gradedAt": "2026-10-15T17:13:47.700Z",
  "note": "C4 and C5 here are the deterministic hard checks only; judge scores are added separately.",
  "models": {
    "bggpt-gemma-3-27b-fp8": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.3,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.536,
        "interval": [
          0.438,
          0.643
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.84,
          "interval": [
            0.68,
            0.96
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.604,
          "interval": [
            0.408,
            0.8
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.38,
          "interval": [
            0.2,
            0.58
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.567,
          "interval": [
            0.4,
            0.717
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.844,
          "interval": [
            0.689,
            0.978
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.2,
          "interval": [
            0,
            0.4
          ]
        }
      }
    },
    "anthropic/claude-fable-5.1": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.1,
      "answersInLeva": 0,
      "deterministic": {
        "items": 85,
        "score": 0.806,
        "interval": [
          0.724,
          0.882
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.96,
          "interval": [
            0.88,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.95,
          "interval": [
            0.85,
            1
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.66,
          "interval": [
            0.5,
            0.82
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.85,
          "interval": [
            0.717,
            0.95
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.822,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.6,
          "interval": [
            0.333,
            0.8
          ]
        }
      }
    },
    "anthropic/claude-opus-5.5": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.011,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.749,
        "interval": [
          0.659,
          0.835
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.76,
          "interval": [
            0.6,
            0.92
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.833,
          "interval": [
            0.683,
            0.983
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.56,
          "interval": [
            0.38,
            0.74
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.9,
          "interval": [
            0.767,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.867,
          "interval": [
            0.689,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "anthropic/claude-sonnet-5.5": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0,
      "answersInLeva": 2,
      "deterministic": {
        "items": 85,
        "score": 0.684,
        "interval": [
          0.582,
          0.778
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.64,
          "interval": [
            0.44,
            0.8
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.783,
          "interval": [
            0.6,
            0.95
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.5,
          "interval": [
            0.32,
            0.7
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.883,
          "interval": [
            0.767,
            0.983
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.844,
          "interval": [
            0.667,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "anthropic/claude-haiku-5.5": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.011,
      "answersInLeva": 0,
      "deterministic": {
        "items": 85,
        "score": 0.582,
        "interval": [
          0.482,
          0.682
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.56,
          "interval": [
            0.36,
            0.76
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.675,
          "interval": [
            0.5,
            0.85
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.36,
          "interval": [
            0.2,
            0.54
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.7,
          "interval": [
            0.55,
            0.85
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.667,
          "interval": [
            0.467,
            0.844
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.867,
          "interval": [
            0.667,
            1
          ]
        }
      }
    },
    "openai/gpt-6-astra": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.849,
        "interval": [
          0.771,
          0.918
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.88,
          "interval": [
            0.72,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.833,
          "interval": [
            0.667,
            0.983
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.74,
          "interval": [
            0.56,
            0.9
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.933,
          "interval": [
            0.833,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 1,
          "interval": [
            1,
            1
          ]
        }
      }
    },
    "openai/gpt-6.1-sol": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0,
      "answersInLeva": 2,
      "deterministic": {
        "items": 85,
        "score": 0.837,
        "interval": [
          0.761,
          0.908
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.92,
          "interval": [
            0.8,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.833,
          "interval": [
            0.667,
            0.967
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.66,
          "interval": [
            0.46,
            0.84
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.917,
          "interval": [
            0.817,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 1,
          "interval": [
            1,
            1
          ]
        }
      }
    },
    "openai/gpt-5.6-luna": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.021,
      "answersInLeva": 5,
      "deterministic": {
        "items": 85,
        "score": 0.729,
        "interval": [
          0.635,
          0.818
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.92,
          "interval": [
            0.8,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.75,
          "interval": [
            0.55,
            0.95
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.48,
          "interval": [
            0.3,
            0.68
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.967,
          "interval": [
            0.917,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 1,
          "interval": [
            1,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.8,
          "interval": [
            0.6,
            1
          ]
        }
      }
    },
    "google/gemini-4-argon": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.432,
      "answersInLeva": 4,
      "deterministic": {
        "items": 85,
        "score": 0.741,
        "interval": [
          0.647,
          0.835
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 1,
          "interval": [
            1,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.95,
          "interval": [
            0.85,
            1
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.64,
          "interval": [
            0.44,
            0.8
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.333,
          "interval": [
            0.167,
            0.517
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.2,
          "interval": [
            0,
            0.4
          ]
        }
      }
    },
    "google/gemini-3.8-flash": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.4,
      "answersInLeva": 2,
      "deterministic": {
        "items": 85,
        "score": 0.735,
        "interval": [
          0.641,
          0.824
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.96,
          "interval": [
            0.88,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.9,
          "interval": [
            0.75,
            1
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.66,
          "interval": [
            0.48,
            0.84
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.333,
          "interval": [
            0.167,
            0.517
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.978,
          "interval": [
            0.933,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.267,
          "interval": [
            0.067,
            0.533
          ]
        }
      }
    },
    "deepseek/deepseek-v4.1-flash": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.079,
      "answersInLeva": 2,
      "deterministic": {
        "items": 85,
        "score": 0.623,
        "interval": [
          0.52,
          0.724
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.84,
          "interval": [
            0.68,
            0.96
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.646,
          "interval": [
            0.45,
            0.833
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.44,
          "interval": [
            0.28,
            0.62
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.717,
          "interval": [
            0.583,
            0.833
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.889,
          "interval": [
            0.733,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.533,
          "interval": [
            0.267,
            0.8
          ]
        }
      }
    },
    "spacexai/grok-4.7": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.026,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.665,
        "interval": [
          0.565,
          0.765
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.6,
          "interval": [
            0.4,
            0.8
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.825,
          "interval": [
            0.65,
            0.975
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.44,
          "interval": [
            0.26,
            0.62
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.883,
          "interval": [
            0.767,
            0.967
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.822,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "mistral/mistral-large-4": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.616,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.532,
        "interval": [
          0.429,
          0.635
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.68,
          "interval": [
            0.48,
            0.84
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.763,
          "interval": [
            0.575,
            0.913
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.44,
          "interval": [
            0.26,
            0.62
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.083,
          "interval": [
            0.017,
            0.167
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.733,
          "interval": [
            0.533,
            0.911
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.133,
          "interval": [
            0,
            0.333
          ]
        }
      }
    },
    "meta/muse-wonder-1.0": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.011,
      "answersInLeva": 0,
      "deterministic": {
        "items": 85,
        "score": 0.846,
        "interval": [
          0.771,
          0.918
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.96,
          "interval": [
            0.88,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.846,
          "interval": [
            0.7,
            0.963
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.68,
          "interval": [
            0.5,
            0.84
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.983,
          "interval": [
            0.95,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.889,
          "interval": [
            0.711,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "openai/gpt-6-luna": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.037,
      "answersInLeva": 5,
      "deterministic": {
        "items": 85,
        "score": 0.808,
        "interval": [
          0.72,
          0.884
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.96,
          "interval": [
            0.88,
            1
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.833,
          "interval": [
            0.683,
            0.967
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.56,
          "interval": [
            0.38,
            0.74
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.9,
          "interval": [
            0.783,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 1,
          "interval": [
            1,
            1
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "alibaba/qwen3.8-max-prime": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.005,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.617,
        "interval": [
          0.515,
          0.714
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.6,
          "interval": [
            0.4,
            0.8
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.721,
          "interval": [
            0.533,
            0.888
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.36,
          "interval": [
            0.2,
            0.56
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.9,
          "interval": [
            0.767,
            1
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.867,
          "interval": [
            0.733,
            0.978
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "moonshotai/kimi-k3": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.042,
      "answersInLeva": 2,
      "deterministic": {
        "items": 85,
        "score": 0.602,
        "interval": [
          0.496,
          0.7
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.64,
          "interval": [
            0.44,
            0.84
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.558,
          "interval": [
            0.35,
            0.775
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.4,
          "interval": [
            0.24,
            0.6
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.833,
          "interval": [
            0.7,
            0.95
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.8,
          "interval": [
            0.644,
            0.911
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "zai/glm-5.3": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.026,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.603,
        "interval": [
          0.5,
          0.703
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.56,
          "interval": [
            0.36,
            0.76
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.663,
          "interval": [
            0.463,
            0.85
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.4,
          "interval": [
            0.22,
            0.56
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.85,
          "interval": [
            0.733,
            0.95
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.778,
          "interval": [
            0.6,
            0.933
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.933,
          "interval": [
            0.8,
            1
          ]
        }
      }
    },
    "deepseek/deepseek-v4-pro-0813": {
      "answers": 190,
      "noText": 0,
      "unverifiedContactRate": 0.189,
      "answersInLeva": 1,
      "deterministic": {
        "items": 85,
        "score": 0.667,
        "interval": [
          0.567,
          0.759
        ]
      },
      "categories": {
        "C1": {
          "items": 25,
          "score": 0.84,
          "interval": [
            0.68,
            0.96
          ]
        },
        "C2": {
          "items": 20,
          "score": 0.708,
          "interval": [
            0.517,
            0.883
          ]
        },
        "C3": {
          "items": 25,
          "score": 0.54,
          "interval": [
            0.36,
            0.72
          ]
        },
        "C4": {
          "items": 20,
          "score": 0.6,
          "interval": [
            0.45,
            0.767
          ]
        },
        "C5": {
          "items": 15,
          "score": 0.8,
          "interval": [
            0.6,
            0.956
          ]
        },
        "C6": {
          "items": 15,
          "score": 0.533,
          "interval": [
            0.267,
            0.8
          ]
        }
      }
    }
  }
}
