{
  "model": "Qwen3-1.7B",
  "total_examples": 5000,
  "exact_match_accuracy": 0.8224,
  "error_detection": {
    "precision": 0.99457111834962,
    "recall": 0.9803781662504459,
    "f1": 0.9874236435501258,
    "true_positives": 2748,
    "false_positives": 15,
    "true_negatives": 1364,
    "false_negatives": 55
  },
  "has_error_accuracy": 0.7589063794531897,
  "no_error_accuracy": 0.9891225525743292,
  "inference_speed_tokens_per_sec": 75.49899709914501,
  "total_inference_time_sec": 896.7403886318207,
  "total_tokens_generated": 67703
}