{
  "models": [
    "SWE-2",
    "Beam 1.0",
    "DeepSeek V4.1 Flash",
    "Claude Fable 5.1",
    "GLM 5.3",
    "GLM 5.3 Flash",
    "GPT-5.5",
    "GPT-5.6 Sol",
    "GPT-6 Astra",
    "GPT-6 Luna",
    "GPT-6 Sol",
    "GPT-6.1 Sol",
    "Gemini 4 Argon",
    "Grok 4.7",
    "Claude Haiku 5.5",
    "Inkling Small",
    "Kimi K3",
    "Mistral Large 4",
    "Muse Wonder 1.0",
    "Claude Opus 4.8",
    "Claude Opus 5",
    "Claude Opus 5.5",
    "Claude Sonnet 5.5",
    "SWE-1.6",
    "SWE-1.7"
  ],
  "colors": {
    "SWE-2": "#3ABBDED9",
    "Beam 1.0": "#786FE1D9",
    "DeepSeek V4.1 Flash": "#786FE1D9",
    "Claude Fable 5.1": "#FF5833D9",
    "GLM 5.3": "#786FE1D9",
    "GLM 5.3 Flash": "#786FE1D9",
    "GPT-5.5": "#10B552D9",
    "GPT-5.6 Sol": "#10B552D9",
    "GPT-6 Astra": "#10B552D9",
    "GPT-6 Luna": "#10B552D9",
    "GPT-6 Sol": "#10B552D9",
    "GPT-6.1 Sol": "#10B552D9",
    "Gemini 4 Argon": "#D1A700D9",
    "Grok 4.7": "#786FE1D9",
    "Claude Haiku 5.5": "#FF5833D9",
    "Inkling Small": "#D1A700D9",
    "Kimi K3": "#459487D9",
    "Mistral Large 4": "#DB58C8D9",
    "Muse Wonder 1.0": "#2050CFD9",
    "Claude Opus 4.8": "#FF5833D9",
    "Claude Opus 5": "#FF5833D9",
    "Claude Opus 5.5": "#FF5833D9",
    "Claude Sonnet 5.5": "#FF5833D9",
    "SWE-1.6": "#3ABBDED9",
    "SWE-1.7": "#3ABBDED9"
  },
  "lab_colors": {
    "Anthropic": "#FF5833D9",
    "OpenAI": "#10B552D9",
    "xAI": "#786FE1D9",
    "Cognition": "#3ABBDED9",
    "Moonshot": "#459487D9",
    "Cursor": "#D1A700D9",
    "Zhipu": "#786FE1D9",
    "DeepSeek": "#786FE1D9",
    "MiniMax": "#2050CFD9",
    "Thinking Machines": "#D1A700D9",
    "Alibaba": "#D1A700D9",
    "NVIDIA": "#10B552D9",
    "Google": "#D1A700D9",
    "Mistral": "#DB58C8D9"
  },
  "harness": {
    "SWE-2": "devin",
    "Beam 1.0": "devin-cli",
    "DeepSeek V4.1 Flash": "devin-cli",
    "Claude Fable 5.1": "claude-code",
    "GLM 5.3": "devin-cli",
    "GLM 5.3 Flash": "devin-cli",
    "GPT-5.5": "codex",
    "GPT-5.6 Sol": "codex",
    "GPT-6 Astra": "codex",
    "GPT-6 Luna": "codex",
    "GPT-6 Sol": "codex",
    "GPT-6.1 Sol": "codex",
    "Gemini 4 Argon": "devin-cli",
    "Grok 4.7": "grok-build",
    "Claude Haiku 5.5": "claude-code",
    "Inkling Small": "devin-cli",
    "Kimi K3": "devin-cli",
    "Mistral Large 4": "vibe",
    "Muse Wonder 1.0": "muse",
    "Claude Opus 4.8": "claude-code",
    "Claude Opus 5": "claude-code",
    "Claude Opus 5.5": "claude-code",
    "Claude Sonnet 5.5": "claude-code",
    "SWE-1.6": "devin-cli-swe1",
    "SWE-1.7": "devin-cli-swe1"
  },
  "efforts": {
    "SWE-2": [
      "medium",
      "high",
      "max"
    ],
    "Beam 1.0": [
      "minimal",
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "DeepSeek V4.1 Flash": [
      "low",
      "high",
      "max"
    ],
    "Claude Fable 5.1": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "GLM 5.3": [
      "low",
      "high",
      "max"
    ],
    "GLM 5.3 Flash": [
      "low",
      "high",
      "max"
    ],
    "GPT-5.5": [
      "low",
      "medium",
      "high",
      "xhigh"
    ],
    "GPT-5.6 Sol": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "GPT-6 Astra": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "GPT-6 Luna": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "GPT-6 Sol": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "GPT-6.1 Sol": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "Gemini 4 Argon": [
      "low",
      "medium",
      "high"
    ],
    "Grok 4.7": [
      "low",
      "medium",
      "high",
      "xhigh"
    ],
    "Claude Haiku 5.5": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "Inkling Small": [
      "high",
      "max"
    ],
    "Kimi K3": [
      "low",
      "high",
      "max"
    ],
    "Mistral Large 4": [
      "low",
      "high",
      "max"
    ],
    "Muse Wonder 1.0": [
      "low",
      "medium",
      "high",
      "xhigh"
    ],
    "Claude Opus 4.8": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "Claude Opus 5": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "Claude Opus 5.5": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "Claude Sonnet 5.5": [
      "low",
      "medium",
      "high",
      "xhigh",
      "max"
    ],
    "SWE-1.6": [
      "na"
    ],
    "SWE-1.7": [
      "na"
    ]
  },
  "subsets": {
    "main": 132
  },
  "data": {
    "SWE-2": {
      "medium": {
        "main": {
          "correct": 0.176,
          "new_score": 0.1556,
          "tokens": 28705,
          "cost": 0.442,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0197
        }
      },
      "high": {
        "main": {
          "correct": 0.2595,
          "new_score": 0.2306,
          "tokens": 68546,
          "cost": 0.958,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0288
        }
      },
      "max": {
        "main": {
          "correct": 0.2667,
          "new_score": 0.2378,
          "tokens": 97584,
          "cost": 1.261,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0242
        }
      }
    },
    "Beam 1.0": {
      "minimal": {
        "main": {
          "correct": 0.0,
          "new_score": 0.0,
          "tokens": 1550,
          "cost": 0.059,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0025
        }
      },
      "low": {
        "main": {
          "correct": 0.0,
          "new_score": 0.0,
          "tokens": 3490,
          "cost": 0.142,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0051
        }
      },
      "medium": {
        "main": {
          "correct": 0.0101,
          "new_score": 0.0083,
          "tokens": null,
          "cost": 0.315,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0127
        }
      },
      "high": {
        "main": {
          "correct": 0.0202,
          "new_score": 0.0174,
          "tokens": null,
          "cost": 0.612,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0227
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.0278,
          "new_score": 0.0243,
          "tokens": null,
          "cost": 1.126,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0379
        }
      },
      "max": {
        "main": {
          "correct": 0.0329,
          "new_score": 0.029,
          "tokens": null,
          "cost": 1.299,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0278
        }
      }
    },
    "DeepSeek V4.1 Flash": {
      "low": {
        "main": {
          "correct": 0.182,
          "new_score": 0.1596,
          "tokens": 40659,
          "cost": 0.206,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0265
        }
      },
      "high": {
        "main": {
          "correct": 0.2062,
          "new_score": 0.1821,
          "tokens": 57169,
          "cost": 0.274,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0286
        }
      },
      "max": {
        "main": {
          "correct": 0.2177,
          "new_score": 0.193,
          "tokens": 82220,
          "cost": 0.384,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0228
        }
      }
    },
    "Claude Fable 5.1": {
      "low": {
        "main": {
          "correct": 0.2288,
          "new_score": 0.2059,
          "tokens": 28797,
          "cost": 3.007,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "medium": {
        "main": {
          "correct": 0.2379,
          "new_score": 0.2147,
          "tokens": 37911,
          "cost": 3.891,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0182
        }
      },
      "high": {
        "main": {
          "correct": 0.2848,
          "new_score": 0.2567,
          "tokens": 54242,
          "cost": 5.386,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0182
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.3576,
          "new_score": 0.3244,
          "tokens": 92813,
          "cost": 8.68,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0212
        }
      },
      "max": {
        "main": {
          "correct": 0.3485,
          "new_score": 0.3167,
          "tokens": 119089,
          "cost": 11.457,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0197
        }
      }
    },
    "GLM 5.3": {
      "low": {
        "main": {
          "correct": 0.1616,
          "new_score": 0.1437,
          "tokens": 47199,
          "cost": 3.189,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0177
        }
      },
      "high": {
        "main": {
          "correct": 0.1894,
          "new_score": 0.1684,
          "tokens": 73247,
          "cost": 5.181,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0227
        }
      },
      "max": {
        "main": {
          "correct": 0.202,
          "new_score": 0.1781,
          "tokens": 100706,
          "cost": 7.516,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0429
        }
      }
    },
    "GLM 5.3 Flash": {
      "low": {
        "main": {
          "correct": 0.0888,
          "new_score": 0.0781,
          "tokens": 35321,
          "cost": 0.43,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0254
        }
      },
      "high": {
        "main": {
          "correct": 0.1414,
          "new_score": 0.1241,
          "tokens": 56914,
          "cost": 0.584,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0253
        }
      },
      "max": {
        "main": {
          "correct": 0.1587,
          "new_score": 0.1418,
          "tokens": 90044,
          "cost": 0.792,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0234
        }
      }
    },
    "GPT-5.5": {
      "low": {
        "main": {
          "correct": 0.0821,
          "new_score": 0.072,
          "tokens": 10332,
          "cost": 1.9753,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0046
        }
      },
      "medium": {
        "main": {
          "correct": 0.1591,
          "new_score": 0.1422,
          "tokens": 16320,
          "cost": 2.9515,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0076
        }
      },
      "high": {
        "main": {
          "correct": 0.2158,
          "new_score": 0.1909,
          "tokens": 21907,
          "cost": 3.8021,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0076
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.253,
          "new_score": 0.2262,
          "tokens": 30925,
          "cost": 5.2771,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      }
    },
    "GPT-5.6 Sol": {
      "low": {
        "main": {
          "correct": 0.1442,
          "new_score": 0.1279,
          "tokens": 9806,
          "cost": 1.451,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0061
        }
      },
      "medium": {
        "main": {
          "correct": 0.2212,
          "new_score": 0.1952,
          "tokens": 15446,
          "cost": 2.36,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      },
      "high": {
        "main": {
          "correct": 0.2727,
          "new_score": 0.2429,
          "tokens": 20920,
          "cost": 3.166,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.2697,
          "new_score": 0.2408,
          "tokens": 26415,
          "cost": 3.83,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "max": {
        "main": {
          "correct": 0.3061,
          "new_score": 0.2764,
          "tokens": 38352,
          "cost": 5.503,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      }
    },
    "GPT-6 Astra": {
      "low": {
        "main": {
          "correct": 0.3424,
          "new_score": 0.3111,
          "tokens": 8987,
          "cost": 2.437,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0076
        }
      },
      "medium": {
        "main": {
          "correct": 0.4015,
          "new_score": 0.3675,
          "tokens": 14065,
          "cost": 3.493,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      },
      "high": {
        "main": {
          "correct": 0.4136,
          "new_score": 0.3831,
          "tokens": 18433,
          "cost": 4.277,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0242
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.4485,
          "new_score": 0.4141,
          "tokens": 20869,
          "cost": 4.539,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "max": {
        "main": {
          "correct": 0.4621,
          "new_score": 0.4277,
          "tokens": 36354,
          "cost": 6.676,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0227
        }
      }
    },
    "GPT-6 Luna": {
      "low": {
        "main": {
          "correct": 0.0455,
          "new_score": 0.0405,
          "tokens": 6519,
          "cost": 0.023,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.003
        }
      },
      "medium": {
        "main": {
          "correct": 0.1773,
          "new_score": 0.1597,
          "tokens": 31360,
          "cost": 0.092,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0015
        }
      },
      "high": {
        "main": {
          "correct": 0.1848,
          "new_score": 0.165,
          "tokens": 42170,
          "cost": 0.115,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.003
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.2045,
          "new_score": 0.1844,
          "tokens": 50565,
          "cost": 0.132,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0045
        }
      },
      "max": {
        "main": {
          "correct": 0.2424,
          "new_score": 0.2187,
          "tokens": 79659,
          "cost": 0.174,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      }
    },
    "GPT-6 Sol": {
      "low": {
        "main": {
          "correct": 0.1167,
          "new_score": 0.1049,
          "tokens": 6487,
          "cost": 0.4164,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0076
        }
      },
      "medium": {
        "main": {
          "correct": 0.2409,
          "new_score": 0.2163,
          "tokens": 13750,
          "cost": 0.8225,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      },
      "high": {
        "main": {
          "correct": 0.253,
          "new_score": 0.2281,
          "tokens": 19393,
          "cost": 1.0714,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0182
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.3348,
          "new_score": 0.3032,
          "tokens": 28587,
          "cost": 1.4432,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0136
        }
      },
      "max": {
        "main": {
          "correct": 0.3758,
          "new_score": 0.3425,
          "tokens": 54181,
          "cost": 2.3547,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      }
    },
    "GPT-6.1 Sol": {
      "low": {
        "main": {
          "correct": 0.2833,
          "new_score": 0.256,
          "tokens": 10042,
          "cost": 0.341,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "medium": {
        "main": {
          "correct": 0.3227,
          "new_score": 0.2958,
          "tokens": 15686,
          "cost": 0.492,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0136
        }
      },
      "high": {
        "main": {
          "correct": 0.3803,
          "new_score": 0.3482,
          "tokens": 22419,
          "cost": 0.647,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.353,
          "new_score": 0.3233,
          "tokens": 24789,
          "cost": 0.695,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      },
      "max": {
        "main": {
          "correct": 0.4227,
          "new_score": 0.3895,
          "tokens": 41479,
          "cost": 1.029,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      }
    },
    "Gemini 4 Argon": {
      "low": {
        "main": {
          "correct": 0.2379,
          "new_score": 0.2147,
          "tokens": 63291,
          "cost": 3.977,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0136
        }
      },
      "medium": {
        "main": {
          "correct": 0.2606,
          "new_score": 0.2345,
          "tokens": 123879,
          "cost": 5.688,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "high": {
        "main": {
          "correct": 0.2909,
          "new_score": 0.263,
          "tokens": 148569,
          "cost": 6.514,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      }
    },
    "Grok 4.7": {
      "low": {
        "main": {
          "correct": 0.2337,
          "new_score": 0.208,
          "tokens": 38161,
          "cost": 3.873,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0106
        }
      },
      "medium": {
        "main": {
          "correct": 0.2924,
          "new_score": 0.2594,
          "tokens": 72180,
          "cost": 8.028,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "high": {
        "main": {
          "correct": 0.297,
          "new_score": 0.2655,
          "tokens": 94341,
          "cost": 11.094,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.3197,
          "new_score": 0.2862,
          "tokens": 110790,
          "cost": 14.36,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      }
    },
    "Claude Haiku 5.5": {
      "low": {
        "main": {
          "correct": 0.1168,
          "new_score": 0.1046,
          "tokens": 39366,
          "cost": 0.065,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "medium": {
        "main": {
          "correct": 0.15,
          "new_score": 0.1342,
          "tokens": 57582,
          "cost": 0.097,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "high": {
        "main": {
          "correct": 0.2076,
          "new_score": 0.1864,
          "tokens": 80993,
          "cost": 0.139,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0197
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.2477,
          "new_score": 0.2228,
          "tokens": 127735,
          "cost": 0.226,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      },
      "max": {
        "main": {
          "correct": 0.305,
          "new_score": 0.2772,
          "tokens": 205112,
          "cost": 0.366,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0258
        }
      }
    },
    "Inkling Small": {
      "high": {
        "main": {
          "correct": 0.0154,
          "new_score": 0.0127,
          "tokens": 13658,
          "cost": 1.366,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0256
        }
      },
      "max": {
        "main": {
          "correct": 0.0379,
          "new_score": 0.0321,
          "tokens": 39077,
          "cost": 3.684,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0606
        }
      }
    },
    "Kimi K3": {
      "low": {
        "main": {
          "correct": 0.1237,
          "new_score": 0.111,
          "tokens": 28740,
          "cost": 2.977,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0177
        }
      },
      "high": {
        "main": {
          "correct": 0.1975,
          "new_score": 0.1774,
          "tokens": 49854,
          "cost": 4.475,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0203
        }
      },
      "max": {
        "main": {
          "correct": 0.1944,
          "new_score": 0.1731,
          "tokens": 64271,
          "cost": 5.456,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0202
        }
      }
    },
    "Mistral Large 4": {
      "low": {
        "main": {
          "correct": 0.1061,
          "new_score": 0.095,
          "tokens": 28384,
          "cost": 0.669,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0
        }
      },
      "high": {
        "main": {
          "correct": 0.0985,
          "new_score": 0.0878,
          "tokens": 51238,
          "cost": 1.031,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0
        }
      },
      "max": {
        "main": {
          "correct": 0.2197,
          "new_score": 0.1965,
          "tokens": 88069,
          "cost": 1.549,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0
        }
      }
    },
    "Muse Wonder 1.0": {
      "low": {
        "main": {
          "correct": 0.2413,
          "new_score": 0.2121,
          "tokens": 20301,
          "cost": 1.843,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "medium": {
        "main": {
          "correct": 0.2606,
          "new_score": 0.2314,
          "tokens": 26714,
          "cost": 2.534,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0182
        }
      },
      "high": {
        "main": {
          "correct": 0.2742,
          "new_score": 0.2428,
          "tokens": 32832,
          "cost": 3.143,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0167
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.2747,
          "new_score": 0.2411,
          "tokens": 38672,
          "cost": 3.793,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0197
        }
      }
    },
    "Claude Opus 4.8": {
      "low": {
        "main": {
          "correct": 0.1061,
          "new_score": 0.0955,
          "tokens": 40687,
          "cost": 4.195,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0091
        }
      },
      "medium": {
        "main": {
          "correct": 0.1227,
          "new_score": 0.1102,
          "tokens": 57192,
          "cost": 5.588,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0106
        }
      },
      "high": {
        "main": {
          "correct": 0.1212,
          "new_score": 0.1086,
          "tokens": 62298,
          "cost": 6.316,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0061
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.1591,
          "new_score": 0.1428,
          "tokens": 88364,
          "cost": 9.133,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0106
        }
      },
      "max": {
        "main": {
          "correct": 0.1636,
          "new_score": 0.1472,
          "tokens": 125863,
          "cost": 12.129,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      }
    },
    "Claude Opus 5": {
      "low": {
        "main": {
          "correct": 0.2091,
          "new_score": 0.1869,
          "tokens": 26898,
          "cost": 3.276,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0182
        }
      },
      "medium": {
        "main": {
          "correct": 0.2682,
          "new_score": 0.2397,
          "tokens": 39813,
          "cost": 5.217,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "high": {
        "main": {
          "correct": 0.297,
          "new_score": 0.2672,
          "tokens": 59260,
          "cost": 8.361,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0212
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.2985,
          "new_score": 0.2674,
          "tokens": 76436,
          "cost": 11.093,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "max": {
        "main": {
          "correct": 0.297,
          "new_score": 0.2658,
          "tokens": 88196,
          "cost": 12.997,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      }
    },
    "Claude Opus 5.5": {
      "low": {
        "main": {
          "correct": 0.1636,
          "new_score": 0.1472,
          "tokens": 14230,
          "cost": 0.746,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0121
        }
      },
      "medium": {
        "main": {
          "correct": 0.3303,
          "new_score": 0.301,
          "tokens": 30068,
          "cost": 1.699,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "high": {
        "main": {
          "correct": 0.3788,
          "new_score": 0.3453,
          "tokens": 41233,
          "cost": 2.423,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0152
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.4727,
          "new_score": 0.4338,
          "tokens": 88053,
          "cost": 5.184,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0212
        }
      },
      "max": {
        "main": {
          "correct": 0.497,
          "new_score": 0.4545,
          "tokens": 201919,
          "cost": 12.821,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0288
        }
      }
    },
    "Claude Sonnet 5.5": {
      "low": {
        "main": {
          "correct": 0.1062,
          "new_score": 0.0941,
          "tokens": 11265,
          "cost": 0.369,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0106
        }
      },
      "medium": {
        "main": {
          "correct": 0.1576,
          "new_score": 0.1417,
          "tokens": 14449,
          "cost": 0.482,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0136
        }
      },
      "high": {
        "main": {
          "correct": 0.2428,
          "new_score": 0.219,
          "tokens": 27839,
          "cost": 1.066,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0137
        }
      },
      "xhigh": {
        "main": {
          "correct": 0.3803,
          "new_score": 0.3475,
          "tokens": 80433,
          "cost": 3.315,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0227
        }
      },
      "max": {
        "main": {
          "correct": 0.45,
          "new_score": 0.4096,
          "tokens": 514722,
          "cost": 19.941,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0379
        }
      }
    },
    "SWE-1.6": {
      "na": {
        "main": {
          "correct": 0.0152,
          "new_score": 0.0134,
          "tokens": 23990,
          "cost": 1.3592,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0
        }
      }
    },
    "SWE-1.7": {
      "na": {
        "main": {
          "correct": 0.189,
          "new_score": 0.1615,
          "tokens": 89251,
          "cost": 3.5209,
          "duration_min": null,
          "tool_calls": null,
          "ote": null,
          "flagged_rate": 0.0076
        }
      }
    }
  }
}
