diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index 55172088e..74b1c4597 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -807,31 +807,31 @@ seconds_per_case: 290.0 total_cost: 1.1164 -- dirname: 2025-03-25-19-46-45--gemini-25-pro-exp-diff-fenced +- dirname: 2025-04-12-04-55-50--gemini-25-pro-diff-fenced test_cases: 225 - model: Gemini 2.5 Pro exp-03-25 + model: gemini/gemini-2.5-pro-preview-03-25 edit_format: diff-fenced - commit_hash: 33413ec - pass_rate_1: 39.1 + commit_hash: 0282574 + pass_rate_1: 40.9 pass_rate_2: 72.9 - pass_num_1: 88 + pass_num_1: 92 pass_num_2: 164 - percent_cases_well_formed: 89.8 - error_outputs: 30 - num_malformed_responses: 30 - num_with_malformed_responses: 23 - user_asks: 57 + percent_cases_well_formed: 92.4 + error_outputs: 21 + num_malformed_responses: 21 + num_with_malformed_responses: 17 + user_asks: 69 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 - test_timeouts: 3 + test_timeouts: 2 total_tests: 225 - command: aider --model gemini/gemini-2.5-pro-exp-03-25 - date: 2025-03-25 - versions: 0.78.1.dev - seconds_per_case: 47.1 - total_cost: 0.0000 + command: aider --model gemini/gemini-2.5-pro-preview-03-25 + date: 2025-04-12 + versions: 0.81.3.dev + seconds_per_case: 45.3 + total_cost: 6.3174 - dirname: 2025-03-29-05-24-55--chatgpt4o-mar28-diff test_cases: 225