{
  "runId": "6d5384a1-ae22-496a-83dd-92c789967f27",
  "generatedAt": "2026-07-10T17:29:33.033Z",
  "models": [
    {
      "adapterId": "codex",
      "model": "gpt-5.4@low",
      "label": "codex/gpt-5.4@low",
      "attempts": 38,
      "scored": 37,
      "pass": 32,
      "partial": 3,
      "incorrect": 2,
      "protocol_error": 1,
      "otherErrors": 0,
      "passRate": 0.8648648648648649,
      "quality": 0.9054054054054054,
      "coverage": 0.9736842105263158,
      "passAtKRate": 0.8648648648648649,
      "fixturesPassed": 32,
      "fixturesAttempted": 38,
      "avgDurationMs": 6128,
      "minDurationMs": 3559,
      "maxDurationMs": 17875,
      "totalDurationMs": 232852,
      "totalPromptTokens": 17583,
      "totalCompletionTokens": 3096,
      "totalReasoningTokens": 11,
      "totalTokens": 20679,
      "totalCachedTokens": 14336,
      "totalCost": 0,
      "totalAnswerBytes": 12183,
      "rank": 1,
      "passRateLabel": "86.5%",
      "qualityLabel": "0.905",
      "coverageLabel": "97.4%",
      "passAtKLabel": "86.5%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4@medium",
      "label": "codex/gpt-5.4@medium",
      "attempts": 38,
      "scored": 36,
      "pass": 32,
      "partial": 2,
      "incorrect": 2,
      "protocol_error": 2,
      "otherErrors": 0,
      "passRate": 0.8888888888888888,
      "quality": 0.9166666666666666,
      "coverage": 0.9473684210526315,
      "passAtKRate": 0.8888888888888888,
      "fixturesPassed": 32,
      "fixturesAttempted": 38,
      "avgDurationMs": 9330,
      "minDurationMs": 3853,
      "maxDurationMs": 20007,
      "totalDurationMs": 354556,
      "totalPromptTokens": 269622,
      "totalCompletionTokens": 4238,
      "totalReasoningTokens": 727,
      "totalTokens": 273860,
      "totalCachedTokens": 215040,
      "totalCost": 0,
      "totalAnswerBytes": 12372,
      "rank": 2,
      "passRateLabel": "88.9%",
      "qualityLabel": "0.917",
      "coverageLabel": "94.7%",
      "passAtKLabel": "88.9%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4-mini@high",
      "label": "codex/gpt-5.4-mini@high",
      "attempts": 38,
      "scored": 36,
      "pass": 31,
      "partial": 3,
      "incorrect": 2,
      "protocol_error": 2,
      "otherErrors": 0,
      "passRate": 0.8611111111111112,
      "quality": 0.9027777777777778,
      "coverage": 0.9473684210526315,
      "passAtKRate": 0.8611111111111112,
      "fixturesPassed": 31,
      "fixturesAttempted": 38,
      "avgDurationMs": 14915,
      "minDurationMs": 5188,
      "maxDurationMs": 28758,
      "totalDurationMs": 566772,
      "totalPromptTokens": 509381,
      "totalCompletionTokens": 14292,
      "totalReasoningTokens": 10399,
      "totalTokens": 523673,
      "totalCachedTokens": 345600,
      "totalCost": 0,
      "totalAnswerBytes": 11886,
      "rank": 3,
      "passRateLabel": "86.1%",
      "qualityLabel": "0.903",
      "coverageLabel": "94.7%",
      "passAtKLabel": "86.1%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4-mini@xhigh",
      "label": "codex/gpt-5.4-mini@xhigh",
      "attempts": 38,
      "scored": 36,
      "pass": 31,
      "partial": 3,
      "incorrect": 2,
      "protocol_error": 2,
      "otherErrors": 0,
      "passRate": 0.8611111111111112,
      "quality": 0.9027777777777778,
      "coverage": 0.9473684210526315,
      "passAtKRate": 0.8611111111111112,
      "fixturesPassed": 31,
      "fixturesAttempted": 38,
      "avgDurationMs": 26702,
      "minDurationMs": 5905,
      "maxDurationMs": 127769,
      "totalDurationMs": 1014661,
      "totalPromptTokens": 31716,
      "totalCompletionTokens": 3972,
      "totalReasoningTokens": 1032,
      "totalTokens": 35688,
      "totalCachedTokens": 27648,
      "totalCost": 0,
      "totalAnswerBytes": 11406,
      "rank": 4,
      "passRateLabel": "86.1%",
      "qualityLabel": "0.903",
      "coverageLabel": "94.7%",
      "passAtKLabel": "86.1%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4@xhigh",
      "label": "codex/gpt-5.4@xhigh",
      "attempts": 38,
      "scored": 36,
      "pass": 30,
      "partial": 3,
      "incorrect": 3,
      "protocol_error": 2,
      "otherErrors": 0,
      "passRate": 0.8333333333333334,
      "quality": 0.875,
      "coverage": 0.9473684210526315,
      "passAtKRate": 0.8333333333333334,
      "fixturesPassed": 30,
      "fixturesAttempted": 38,
      "avgDurationMs": 21365,
      "minDurationMs": 5455,
      "maxDurationMs": 69771,
      "totalDurationMs": 811857,
      "totalPromptTokens": 373440,
      "totalCompletionTokens": 18994,
      "totalReasoningTokens": 14687,
      "totalTokens": 392434,
      "totalCachedTokens": 344064,
      "totalCost": 0,
      "totalAnswerBytes": 14336,
      "rank": 5,
      "passRateLabel": "83.3%",
      "qualityLabel": "0.875",
      "coverageLabel": "94.7%",
      "passAtKLabel": "83.3%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4-mini@medium",
      "label": "codex/gpt-5.4-mini@medium",
      "attempts": 38,
      "scored": 35,
      "pass": 33,
      "partial": 2,
      "incorrect": 0,
      "protocol_error": 3,
      "otherErrors": 0,
      "passRate": 0.9428571428571428,
      "quality": 0.9714285714285714,
      "coverage": 0.9210526315789473,
      "passAtKRate": 0.9428571428571428,
      "fixturesPassed": 33,
      "fixturesAttempted": 38,
      "avgDurationMs": 12052,
      "minDurationMs": 3880,
      "maxDurationMs": 45198,
      "totalDurationMs": 457960,
      "totalPromptTokens": 193026,
      "totalCompletionTokens": 5899,
      "totalReasoningTokens": 2606,
      "totalTokens": 198925,
      "totalCachedTokens": 125952,
      "totalCost": 0,
      "totalAnswerBytes": 11789,
      "rank": 6,
      "passRateLabel": "94.3%",
      "qualityLabel": "0.971",
      "coverageLabel": "92.1%",
      "passAtKLabel": "94.3%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4@high",
      "label": "codex/gpt-5.4@high",
      "attempts": 38,
      "scored": 35,
      "pass": 31,
      "partial": 2,
      "incorrect": 2,
      "protocol_error": 3,
      "otherErrors": 0,
      "passRate": 0.8857142857142857,
      "quality": 0.9142857142857143,
      "coverage": 0.9210526315789473,
      "passAtKRate": 0.8857142857142857,
      "fixturesPassed": 31,
      "fixturesAttempted": 38,
      "avgDurationMs": 11221,
      "minDurationMs": 4487,
      "maxDurationMs": 34907,
      "totalDurationMs": 426403,
      "totalPromptTokens": 76881,
      "totalCompletionTokens": 4835,
      "totalReasoningTokens": 1404,
      "totalTokens": 81716,
      "totalCachedTokens": 43008,
      "totalCost": 0,
      "totalAnswerBytes": 13173,
      "rank": 7,
      "passRateLabel": "88.6%",
      "qualityLabel": "0.914",
      "coverageLabel": "92.1%",
      "passAtKLabel": "88.6%"
    },
    {
      "adapterId": "codex",
      "model": "gpt-5.4-mini@low",
      "label": "codex/gpt-5.4-mini@low",
      "attempts": 38,
      "scored": 34,
      "pass": 31,
      "partial": 1,
      "incorrect": 2,
      "protocol_error": 4,
      "otherErrors": 0,
      "passRate": 0.9117647058823529,
      "quality": 0.9264705882352942,
      "coverage": 0.8947368421052632,
      "passAtKRate": 0.9117647058823529,
      "fixturesPassed": 31,
      "fixturesAttempted": 38,
      "avgDurationMs": 6062,
      "minDurationMs": 2983,
      "maxDurationMs": 15321,
      "totalDurationMs": 230371,
      "totalPromptTokens": 190916,
      "totalCompletionTokens": 3867,
      "totalReasoningTokens": 468,
      "totalTokens": 194783,
      "totalCachedTokens": 55296,
      "totalCost": 0,
      "totalAnswerBytes": 12194,
      "rank": 8,
      "passRateLabel": "91.2%",
      "qualityLabel": "0.926",
      "coverageLabel": "89.5%",
      "passAtKLabel": "91.2%"
    }
  ]
}