Statistics Summary for op agent (mean ± std):
==================================================
accuracy: 0.0000 ± 0.0000
total_entries: 136.0000 ± 0.0000
correct_matches: 0.0000 ± 0.0000
average_execution_time: 24.5999 ± 0.0558
metrics_by_complexity:
  simple:
    count: 116.0000 ± 0.0000
    full_matches: 0.0000 ± 0.0000
    exact_code_matches: 0.0000 ± 0.0000
    exact_code_match_rate: 0.0000 ± 0.0000
    pv_exact_matched: 0.0000 ± 0.0000
    pv_exact_mismatched: 116.0000 ± 0.0000
    pv_exact_match_rate: 0.0000 ± 0.0000
    average_pv_match_rate: 0.0000 ± 0.0000
    average_pv_mismatch_rate: 100.0000 ± 0.0000
    timing_matched: 0.0000 ± 0.0000
    timing_mismatched: 116.0000 ± 0.0000
    timing_match_rate: 0.0000 ± 0.0000
    temp_matched: 0.0000 ± 0.0000
    temp_mismatched: 0.0000 ± 0.0000
    temp_match_rate: 0.0000 ± 0.0000
    full_matched: 0.0000 ± 0.0000
    full_mismatched: 116.0000 ± 0.0000
    full_match_rate: 0.0000 ± 0.0000
    accuracy: 0.0000 ± 0.0000
    average_timing_score: 0.0000 ± 0.0000
    average_temp_score: 1.0000 ± 0.0000
    average_full_score: 0.0000 ± 0.0000
    average_best_codebleu:
      average_CodeBLEU: 0.3052 ± 0.0000
      comb_7_CodeBLEU: 0.4883 ± 0.0000
      dataflow_match_score: 0.2586 ± 0.0000
      ngram_match_score: 0.0000 ± 0.0000
      syntax_match_score: 0.2207 ± 0.0000
      weighted_ngram_match_score: 0.0000 ± 0.0000
    average_best_levenshtein: 1486.4914 ± 0.0000
    average_best_normalized_levenshtein: 0.9729 ± 0.0000
    average_inference_time: 21.4821 ± 0.0673
  complex:
    count: 20.0000 ± 0.0000
    full_matches: 0.0000 ± 0.0000
    exact_code_matches: 0.0000 ± 0.0000
    exact_code_match_rate: 0.0000 ± 0.0000
    pv_exact_matched: 0.0000 ± 0.0000
    pv_exact_mismatched: 20.0000 ± 0.0000
    pv_exact_match_rate: 0.0000 ± 0.0000
    average_pv_match_rate: 0.0000 ± 0.0000
    average_pv_mismatch_rate: 100.0000 ± 0.0000
    timing_matched: 0.0000 ± 0.0000
    timing_mismatched: 20.0000 ± 0.0000
    timing_match_rate: 0.0000 ± 0.0000
    temp_matched: 0.0000 ± 0.0000
    temp_mismatched: 9.0000 ± 0.0000
    temp_match_rate: 0.0000 ± 0.0000
    full_matched: 0.0000 ± 0.0000
    full_mismatched: 20.0000 ± 0.0000
    full_match_rate: 0.0000 ± 0.0000
    accuracy: 0.0000 ± 0.0000
    average_timing_score: 0.0000 ± 0.0000
    average_temp_score: 0.5500 ± 0.0000
    average_full_score: 0.0000 ± 0.0000
    average_best_codebleu:
      average_CodeBLEU: 0.2349 ± 0.0000
      comb_7_CodeBLEU: 0.3652 ± 0.0000
      dataflow_match_score: 0.6386 ± 0.0000
      ngram_match_score: 0.0024 ± 0.0000
      syntax_match_score: 0.1657 ± 0.0000
      weighted_ngram_match_score: 0.0327 ± 0.0000
    average_best_levenshtein: 1636.0000 ± 0.0000
    average_best_normalized_levenshtein: 0.8852 ± 0.0000
    average_inference_time: 42.6834 ± 0.0289
==================================================
