Statistics Summary for op agent (mean ± std):
==================================================
accuracy: 1.5873 ± nan
total_entries: 126.0000 ± nan
correct_matches: 2.0000 ± nan
average_execution_time: 1.9844 ± nan
metrics_by_complexity:
  complex:
    count: 6.0000 ± nan
    correct_matches: 2.0000 ± nan
    pv_matched: 4.0000 ± nan
    pv_mismatched: 2.0000 ± nan
    pv_match_rate: 66.6667 ± nan
    timing_matched: 4.0000 ± nan
    timing_mismatched: 2.0000 ± nan
    timing_match_rate: 66.6667 ± nan
    temp_matched: 6.0000 ± nan
    temp_mismatched: 0.0000 ± nan
    temp_match_rate: 100.0000 ± nan
    full_matched: 4.0000 ± nan
    full_mismatched: 2.0000 ± nan
    full_match_rate: 66.6667 ± nan
    accuracy: 33.3333 ± nan
    average_best_codebleu:
      codebleu: 0.6591 ± nan
      ngram_match_score: 0.4680 ± nan
      weighted_ngram_match_score: 0.5171 ± nan
      syntax_match_score: 0.8551 ± nan
      dataflow_match_score: 0.7962 ± nan
    average_best_levenshtein: 32.0000 ± nan
    average_best_normalized_levenshtein: 0.1449 ± nan
    average_execution_time: 1.9844 ± nan
==================================================
