{
  "schemaVersion": 1,
  "status": "deadline-stopped-with-complete-first-attempt-coverage",
  "auditedAt": "2026-09-21T22:56:07.474265+00:00",
  "profile": "native-xhigh-research",
  "configurationSha256": "34fe1dbd31e8ae24944f106734e124f67c75a5e16ce767d60fa6a05aa190b19e",
  "coverage": {
    "expected": 14219,
    "unique": 14219,
    "baselinePreserved": 14128,
    "ifevalHashesMatched": 541
  },
  "suites": {
    "aime-2025": {
      "requested": 30,
      "correct": 27,
      "completeCorrect": 27,
      "incorrect": 1,
      "unassessed": 2,
      "providerErrors": 0,
      "emptyAnswers": 2,
      "truncated": 2,
      "scorePercent": 90.0
    },
    "humaneval": {
      "requested": 164,
      "correct": 161,
      "completeCorrect": 161,
      "incorrect": 3,
      "unassessed": 0,
      "providerErrors": 0,
      "emptyAnswers": 0,
      "truncated": 0,
      "scorePercent": 98.17
    },
    "ifeval": {
      "requested": 541,
      "correct": 505,
      "completeCorrect": 505,
      "incorrect": 36,
      "unassessed": 0,
      "providerErrors": 0,
      "emptyAnswers": 0,
      "truncated": 0,
      "grading": "official-prompt-strict",
      "scorePercent": 93.35
    },
    "nexibench-portuguese": {
      "requested": 121,
      "correct": 107,
      "completeCorrect": 107,
      "incorrect": 14,
      "unassessed": 0,
      "providerErrors": 0,
      "emptyAnswers": 0,
      "truncated": 0,
      "scorePercent": 88.43
    },
    "gsm8k": {
      "requested": 1319,
      "correct": 1285,
      "completeCorrect": 1285,
      "incorrect": 34,
      "unassessed": 0,
      "providerErrors": 0,
      "emptyAnswers": 0,
      "truncated": 0,
      "scorePercent": 97.42
    },
    "contexto-longo": {
      "requested": 12,
      "correct": 12,
      "completeCorrect": 12,
      "incorrect": 0,
      "unassessed": 0,
      "providerErrors": 0,
      "emptyAnswers": 0,
      "truncated": 0,
      "scorePercent": 100.0
    },
    "mmlu-pro": {
      "requested": 12032,
      "correct": 10153,
      "completeCorrect": 10153,
      "incorrect": 1775,
      "unassessed": 104,
      "providerErrors": 58,
      "emptyAnswers": 102,
      "truncated": 44,
      "scorePercent": 84.38
    }
  },
  "diagnosticRetries": {
    "requested": 58,
    "correct": 29,
    "completeCorrect": 29,
    "incorrect": 17,
    "unassessed": 12,
    "providerErrors": 4,
    "emptyAnswers": 11,
    "truncated": 8,
    "unfinishedAtDeadline": 4,
    "notPassAtOne": true,
    "identitySelectionFields": {
      "taskSelectionSha256": "2d7c8da1a928ec65ede40e31d5319f2d8b8c7ea2fb147cd3e8b11c40b0946782"
    }
  },
  "evidenceSha256": {
    "quality.jsonl": "15ce589c4ea728fdf825dc23c7ebf32ece86c2430da31301fd26216dd27084dd",
    "quality-identity.json": "34fe1dbd31e8ae24944f106734e124f67c75a5e16ce767d60fa6a05aa190b19e",
    "ifeval-official.jsonl": "13b46dc12b46d2ed895a4bc10d44dfaeb2bae6916add76dfbda9381fe8a8bf9c",
    "campaign/baseline-quality.jsonl": "a3c2f114a7b490629b26fcd5a3ec205af85ab07aa05d728191553b66a1f2f8cd",
    "campaign/transport-retries/quality.jsonl": "0926d1fc78c625a0b47d5c839d4f28b92d2477a2cb4229c370feb3750485232a",
    "campaign/campaign.jsonl": "c2134ad3fabfb0390df137a6d7311a61f80b88dd0c05ee711436db6e6c2b1162"
  },
  "brand": "Nexi Air",
  "cleanRun": false,
  "speed": {
    "hardware": "L40S 48 GB",
    "warmProseMedianTokensPerSecond": 46.69,
    "warmProseRange": [44.51, 48.87],
    "prompts": 2,
    "reasoning": "off",
    "coldFirstAnswerMs": 303479.914802,
    "warmFirstAnswerMs": 1359.858503,
    "latencySmokeOutputTokens": 4,
    "longContextConfiguredTokens": 262144
  },
  "conditions": {
    "reasoning": "native-xhigh",
    "maxOutputTokens": 65536,
    "temperature": 1,
    "topP": 0.95,
    "seed": 20260916,
    "firstAttemptsOnly": true,
    "mixedHardware": true,
    "notAnIndependentEvaluation": true
  }
}
