From 87ba63c14cd1171c2739d4e53b968b7afcb872c8 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Fri, 28 Mar 2025 19:36:06 -1000 Subject: [PATCH] docs: Add chatgpt-4o-latest benchmark results --- aider/website/_data/polyglot_leaderboard.yml | 28 +++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index 8325f757c..aa8d8b0d8 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -831,4 +831,30 @@ date: 2025-03-25 versions: 0.78.1.dev seconds_per_case: 47.1 - total_cost: 0.0000 \ No newline at end of file + total_cost: 0.0000 + +- dirname: 2025-03-29-05-24-55--chatgpt4o-mar28-diff + test_cases: 225 + model: chatgpt-4o-latest (2025-03-29) + edit_format: diff + commit_hash: 0decbad + pass_rate_1: 16.4 + pass_rate_2: 45.3 + pass_num_1: 37 + pass_num_2: 102 + percent_cases_well_formed: 64.4 + error_outputs: 85 + num_malformed_responses: 85 + num_with_malformed_responses: 80 + user_asks: 174 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 0 + test_timeouts: 4 + total_tests: 225 + command: aider --model chatgpt-4o-latest + date: 2025-03-29 + versions: 0.79.3.dev + seconds_per_case: 10.3 + total_cost: 19.7416 \ No newline at end of file