[
  {
    "report": "qwen-exploratory-original-mmlu.json",
    "reason": "Superseded original MMLU sample; documented answer-key concerns; excluded from all comparison totals.",
    "accuracy": [
      {
        "id": "citation-match",
        "category": "grounding",
        "repeat": 0,
        "seed": 42,
        "answer": "{\"signing_source\":\"A\",\"payment_source\":\"C\"}",
        "tool_calls": [],
        "reasoningChars": 447,
        "elapsedSeconds": 14.99819425100577,
        "firstEventSeconds": 0.8107896980072837,
        "firstContentSeconds": 13.838864994002506,
        "usage": {
          "completion_tokens": 148,
          "prompt_tokens": 113,
          "total_tokens": 261,
          "prompt_tokens_details": {
            "cached_tokens": 0
          }
        },
        "timings": {
          "cache_n": 0,
          "prompt_n": 113,
          "prompt_ms": 808.731,
          "prompt_per_token_ms": 7.156911504424778,
          "prompt_per_second": 139.72507545772328,
          "predicted_n": 148,
          "predicted_ms": 14187.316,
          "predicted_per_token_ms": 96.5123537414966,
          "predicted_per_second": 10.361367858444824
        },
        "finishReason": "stop",
        "grade": {
          "passed": true,
          "strictJson": true,
          "expected": {
            "signing_source": "A",
            "payment_source": "C"
          },
          "actual": {
            "signing_source": "A",
            "payment_source": "C"
          }
        }
      },
      {
        "id": "mmlu-law-753",
        "category": "public-law",
        "repeat": 0,
        "seed": 42,
        "answer": "{\"answer\":\"A\"}",
        "tool_calls": [],
        "reasoningChars": 3781,
        "elapsedSeconds": 79.9089739099727,
        "firstEventSeconds": 1.187696093984414,
        "firstContentSeconds": 79.43881566799246,
        "usage": {
          "completion_tokens": 844,
          "prompt_tokens": 262,
          "total_tokens": 1106,
          "prompt_tokens_details": {
            "cached_tokens": 0
          }
        },
        "timings": {
          "cache_n": 0,
          "prompt_n": 262,
          "prompt_ms": 1185.155,
          "prompt_per_token_ms": 4.5234923664122135,
          "prompt_per_second": 221.0681303289443,
          "predicted_n": 844,
          "predicted_ms": 78721.142,
          "predicted_per_token_ms": 93.38213760379598,
          "predicted_per_second": 10.708686111286342
        },
        "finishReason": "stop",
        "grade": {
          "passed": false,
          "strictJson": true,
          "expected": {
            "answer": "D"
          },
          "actual": {
            "answer": "A"
          }
        }
      },
      {
        "id": "mmlu-law-751",
        "category": "public-law",
        "repeat": 0,
        "seed": 42,
        "answer": "{\"answer\":\"B\"}",
        "tool_calls": [],
        "reasoningChars": 6536,
        "elapsedSeconds": 134.55618367900024,
        "firstEventSeconds": 1.1403146240045317,
        "firstContentSeconds": 134.09214658397832,
        "usage": {
          "completion_tokens": 1431,
          "prompt_tokens": 246,
          "total_tokens": 1677,
          "prompt_tokens_details": {
            "cached_tokens": 0
          }
        },
        "timings": {
          "cache_n": 0,
          "prompt_n": 246,
          "prompt_ms": 1138.235,
          "prompt_per_token_ms": 4.626971544715447,
          "prompt_per_second": 216.12408685376923,
          "predicted_n": 1431,
          "predicted_ms": 133415.615,
          "predicted_per_token_ms": 93.29763286713286,
          "predicted_per_second": 10.718385550297093
        },
        "finishReason": "stop",
        "grade": {
          "passed": false,
          "strictJson": true,
          "expected": {
            "answer": "C"
          },
          "actual": {
            "answer": "B"
          }
        }
      }
    ],
    "fixtures": null
  }
]
