From bd28d8f3fb3eb755e4fc8a0d82f600b27bd47cf8 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Tue, 22 Oct 2024 10:52:35 -0700 Subject: [PATCH] corrected 1022 benchmark results --- aider/website/_data/edit_leaderboard.yml | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/aider/website/_data/edit_leaderboard.yml b/aider/website/_data/edit_leaderboard.yml index d1527c83c..c79de9893 100644 --- a/aider/website/_data/edit_leaderboard.yml +++ b/aider/website/_data/edit_leaderboard.yml @@ -1589,25 +1589,25 @@ seconds_per_case: 64.9 total_cost: 0.0000 -- dirname: 2024-10-22-16-18-20--sonnet-1022-diff +- dirname: 2024-10-22-17-45-28--sonnet-1022-diff-fixed-model-settings test_cases: 133 - model: claude-3-5-sonnet-20241022 + model: anthropic/claude-3-5-sonnet-20241022 edit_format: diff - commit_hash: 46269f2-dirty - pass_rate_1: 67.7 - pass_rate_2: 83.5 - percent_cases_well_formed: 98.5 - error_outputs: 5 - num_malformed_responses: 5 - num_with_malformed_responses: 2 - user_asks: 2 + commit_hash: 3b14eb9 + pass_rate_1: 69.2 + pass_rate_2: 84.2 + percent_cases_well_formed: 99.2 + error_outputs: 1 + num_malformed_responses: 1 + num_with_malformed_responses: 1 + user_asks: 0 lazy_comments: 1 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 - test_timeouts: 1 + test_timeouts: 0 command: aider --model anthropic/claude-3-5-sonnet-20241022 date: 2024-10-22 versions: 0.59.2.dev - seconds_per_case: 17.7 + seconds_per_case: 18.6 total_cost: 0.0000 \ No newline at end of file