diff --git a/_data/edit_leaderboard.yml b/_data/edit_leaderboard.yml index 7cac10b94..9155cbf6a 100644 --- a/_data/edit_leaderboard.yml +++ b/_data/edit_leaderboard.yml @@ -402,4 +402,27 @@ date: 2024-05-07 versions: 0.31.2-dev seconds_per_case: 36.6 - total_cost: 0.0000 \ No newline at end of file + total_cost: 0.0000 + +- dirname: 2024-05-13-17-39-05--gpt-4o-diff + test_cases: 133 + model: openai/gpt-4o + edit_format: diff + commit_hash: b6cd852 + pass_rate_1: 60.2 + pass_rate_2: 72.9 + percent_cases_well_formed: 96.2 + error_outputs: 103 + num_malformed_responses: 5 + user_asks: 0 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 2 + exhausted_context_windows: 0 + test_timeouts: 1 + command: aider --model openai/gpt-4o + date: 2024-05-13 + versions: 0.34.1-dev + seconds_per_case: 6.0 + total_cost: 0.0000 + diff --git a/_data/refactor_leaderboard.yml b/_data/refactor_leaderboard.yml index 7af3a87ac..644d4611a 100644 --- a/_data/refactor_leaderboard.yml +++ b/_data/refactor_leaderboard.yml @@ -100,4 +100,24 @@ versions: 0.33.1-dev seconds_per_case: 61.8 total_cost: 18.3844 - \ No newline at end of file + +- dirname: 2024-05-13-17-42-22--refac-gpt-4o-diff + test_cases: 89 + model: openai/gpt-4o + edit_format: diff + commit_hash: b6cd852 + pass_rate_1: 62.9 + percent_cases_well_formed: 53.9 + error_outputs: 9025 + num_malformed_responses: 41 + user_asks: 0 + lazy_comments: 2 + syntax_errors: 0 + indentation_errors: 5 + exhausted_context_windows: 0 + test_timeouts: 0 + command: aider --model openai/gpt-4o + date: 2024-05-13 + versions: 0.34.1-dev + seconds_per_case: 27.8 + total_cost: 0.0000 \ No newline at end of file