{
  "model": "Qwen3-4B",
  "total_examples": 5000,
  "exact_match_accuracy": 0.8564,
  "error_detection": {
    "precision": 0.9969188634029442,
    "recall": 0.9921635434412266,
    "f1": 0.994535519125683,
    "true_positives": 2912,
    "false_positives": 9,
    "true_negatives": 1370,
    "false_negatives": 23
  },
  "has_error_accuracy": 0.8041977354322011,
  "no_error_accuracy": 0.9934735315445975,
  "inference_speed_tokens_per_sec": 58.816495560243375,
  "total_inference_time_sec": 1150.6635911464691,
  "total_tokens_generated": 67678
}