{
  "schema_version": "0.2.2",
  "evaluation_id": "mmlu_pro_chat/RedHatAI/Qwen3.6-35B-A3B-NVFP4/1782388472.716288",
  "evaluation_timestamp": "1782225973",
  "retrieved_timestamp": "1782388472.716288",
  "source_metadata": {
    "source_name": "lm-evaluation-harness",
    "source_type": "evaluation_run",
    "source_organization_name": "RedHatAI",
    "evaluator_relationship": "third_party"
  },
  "eval_library": {
    "name": "lm_eval",
    "version": "0.4.13.dev0"
  },
  "model_info": {
    "name": "RedHatAI/Qwen3.6-35B-A3B-NVFP4",
    "id": "RedHatAI/Qwen3.6-35B-A3B-NVFP4",
    "developer": "RedHatAI",
    "additional_details": {
      "model_args": "{'model': 'RedHatAI/Qwen3.6-35B-A3B-NVFP4', 'max_length': 262144, 'base_url': 'http://0.0.0.0:8703/v1/chat/completions', 'num_concurrent': 64, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 1200}",
      "num_seeds_merged": "3"
    }
  },
  "evaluation_results": [
    {
      "evaluation_name": "mmlu_pro_chat/custom-extract",
      "source_data": {
        "dataset_name": "mmlu_pro_chat",
        "source_type": "other"
      },
      "metric_config": {
        "evaluation_description": "exact_match (filter: custom-extract)",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.8470190602836879,
        "details": {
          "seed_scores": "[0.8468251329787234, 0.846908244680851, 0.8473238031914894]",
          "evaluation_timestamps": "[1782237524, 1782247059, 1782225973]"
        },
        "uncertainty": {
          "standard_error": {
            "value": 0.00015424879108018015,
            "method": "across_seeds"
          },
          "num_samples": 3
        }
      }
    }
  ]
}