Statistics Summary for op agent (mean ± std):
==================================================
accuracy: 76.6667 ± 2.8868
total_entries: 20.0000 ± 0.0000
correct_matches: 15.3333 ± 0.5774
average_execution_time: 1.4703 ± 0.1535
metrics_by_complexity:
  simple:
    count: 20.0000 ± 0.0000
    full_matches: 15.3333 ± 0.5774
    exact_code_matches: 12.3333 ± 0.5774
    exact_code_match_rate: 61.6667 ± 2.8868
    pv_exact_matched: 16.3333 ± 0.5774
    pv_exact_mismatched: 3.6667 ± 0.5774
    pv_exact_match_rate: 81.6667 ± 2.8868
    average_pv_match_rate: 87.3750 ± 4.8446
    average_pv_mismatch_rate: 12.6250 ± 4.8446
    timing_matched: 16.6667 ± 1.1547
    timing_mismatched: 3.3333 ± 1.1547
    timing_match_rate: 83.3333 ± 5.7735
    temp_matched: 0.0000 ± 0.0000
    temp_mismatched: 0.0000 ± 0.0000
    temp_match_rate: 0.0000 ± 0.0000
    full_matched: 15.3333 ± 0.5774
    full_mismatched: 4.6667 ± 0.5774
    full_match_rate: 76.6667 ± 2.8868
    accuracy: 76.6667 ± 2.8868
    average_timing_score: 0.8738 ± 0.0330
    average_temp_score: 1.0000 ± 0.0000
    average_full_score: 0.8738 ± 0.0451
    average_best_codebleu:
      average_CodeBLEU: 0.7837 ± 0.0145
      comb_7_CodeBLEU: 0.8641 ± 0.0178
      dataflow_match_score: 0.0500 ± 0.0000
      ngram_match_score: 0.6567 ± 0.0096
      syntax_match_score: 0.8354 ± 0.0402
      weighted_ngram_match_score: 0.6427 ± 0.0096
    average_best_levenshtein: 6.0000 ± 0.1000
    average_best_normalized_levenshtein: 0.0742 ± 0.0024
    average_inference_time: 1.4703 ± 0.1535
==================================================
