{
  "model": "Qwen3-0.6B",
  "total_examples": 5000,
  "exact_match_accuracy": 0.7876,
  "error_detection": {
    "precision": 0.9930635838150289,
    "recall": 0.9735549678881753,
    "f1": 0.9832125143075162,
    "true_positives": 2577,
    "false_positives": 18,
    "true_negatives": 1361,
    "false_negatives": 70
  },
  "has_error_accuracy": 0.7116818558409279,
  "no_error_accuracy": 0.9869470630891951,
  "inference_speed_tokens_per_sec": 75.62431472234204,
  "total_inference_time_sec": 896.1006820201874,
  "total_tokens_generated": 67767
}