{
  "judgedAt": "2026-10-15T17:13:46.059Z",
  "judges": [
    "openai/gpt-6.1-sol",
    "google/gemini-4-argon"
  ],
  "spentUsd": 0.0985,
  "outcomes": {
    "judged": 3990
  },
  "models": {
    "bggpt-gemma-3-27b-fp8": {
      "C4": {
        "verdicts": 120,
        "score": 0.671,
        "independentScore": 0.671
      },
      "C5": {
        "verdicts": 90,
        "score": 0.932,
        "independentScore": 0.932
      }
    },
    "anthropic/claude-fable-5.1": {
      "C4": {
        "verdicts": 120,
        "score": 0.681,
        "independentScore": 0.681
      },
      "C5": {
        "verdicts": 90,
        "score": 0.971,
        "independentScore": 0.971
      }
    },
    "anthropic/claude-opus-5.5": {
      "C4": {
        "verdicts": 120,
        "score": 0.688,
        "independentScore": 0.688
      },
      "C5": {
        "verdicts": 90,
        "score": 0.966,
        "independentScore": 0.966
      }
    },
    "anthropic/claude-sonnet-5.5": {
      "C4": {
        "verdicts": 120,
        "score": 0.665,
        "independentScore": 0.665
      },
      "C5": {
        "verdicts": 90,
        "score": 0.954,
        "independentScore": 0.954
      }
    },
    "anthropic/claude-haiku-5.5": {
      "C4": {
        "verdicts": 120,
        "score": 0.652,
        "independentScore": 0.652
      },
      "C5": {
        "verdicts": 90,
        "score": 0.884,
        "independentScore": 0.884
      }
    },
    "openai/gpt-6-astra": {
      "C4": {
        "verdicts": 120,
        "score": 0.88,
        "independentScore": 0.921
      },
      "C5": {
        "verdicts": 90,
        "score": 0.994,
        "independentScore": 0.992
      }
    },
    "openai/gpt-6.1-sol": {
      "C4": {
        "verdicts": 120,
        "score": 0.879,
        "independentScore": 0.921
      },
      "C5": {
        "verdicts": 90,
        "score": 0.997,
        "independentScore": 0.994
      }
    },
    "openai/gpt-5.6-luna": {
      "C4": {
        "verdicts": 120,
        "score": 0.786,
        "independentScore": 0.832
      },
      "C5": {
        "verdicts": 90,
        "score": 0.988,
        "independentScore": 0.988
      }
    },
    "google/gemini-4-argon": {
      "C4": {
        "verdicts": 120,
        "score": 0.665,
        "independentScore": 0.523
      },
      "C5": {
        "verdicts": 90,
        "score": 0.98,
        "independentScore": 0.971
      }
    },
    "google/gemini-3.8-flash": {
      "C4": {
        "verdicts": 120,
        "score": 0.676,
        "independentScore": 0.565
      },
      "C5": {
        "verdicts": 90,
        "score": 0.975,
        "independentScore": 0.969
      }
    },
    "deepseek/deepseek-v4.1-flash": {
      "C4": {
        "verdicts": 120,
        "score": 0.607,
        "independentScore": 0.607
      },
      "C5": {
        "verdicts": 90,
        "score": 0.976,
        "independentScore": 0.976
      }
    },
    "spacexai/grok-4.7": {
      "C4": {
        "verdicts": 120,
        "score": 0.788,
        "independentScore": 0.788
      },
      "C5": {
        "verdicts": 90,
        "score": 0.971,
        "independentScore": 0.971
      }
    },
    "mistral/mistral-large-4": {
      "C4": {
        "verdicts": 120,
        "score": 0.604,
        "independentScore": 0.604
      },
      "C5": {
        "verdicts": 90,
        "score": 0.922,
        "independentScore": 0.922
      }
    },
    "meta/muse-wonder-1.0": {
      "C4": {
        "verdicts": 120,
        "score": 0.747,
        "independentScore": 0.747
      },
      "C5": {
        "verdicts": 90,
        "score": 0.961,
        "independentScore": 0.961
      }
    },
    "openai/gpt-6-luna": {
      "C4": {
        "verdicts": 120,
        "score": 0.879,
        "independentScore": 0.911
      },
      "C5": {
        "verdicts": 90,
        "score": 0.979,
        "independentScore": 0.98
      }
    },
    "alibaba/qwen3.8-max-prime": {
      "C4": {
        "verdicts": 120,
        "score": 0.745,
        "independentScore": 0.745
      },
      "C5": {
        "verdicts": 90,
        "score": 0.971,
        "independentScore": 0.971
      }
    },
    "moonshotai/kimi-k3": {
      "C4": {
        "verdicts": 120,
        "score": 0.702,
        "independentScore": 0.702
      },
      "C5": {
        "verdicts": 90,
        "score": 0.929,
        "independentScore": 0.929
      }
    },
    "zai/glm-5.3": {
      "C4": {
        "verdicts": 120,
        "score": 0.602,
        "independentScore": 0.602
      },
      "C5": {
        "verdicts": 90,
        "score": 0.911,
        "independentScore": 0.911
      }
    },
    "deepseek/deepseek-v4-pro-0813": {
      "C4": {
        "verdicts": 120,
        "score": 0.778,
        "independentScore": 0.778
      },
      "C5": {
        "verdicts": 90,
        "score": 0.942,
        "independentScore": 0.942
      }
    }
  }
}
