From 1a6a16e061a2af367491731f7291b9b041909f4f Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Fri, 31 Jan 2025 15:13:34 -0800 Subject: [PATCH] chore: Update polyglot leaderboard with new test run data --- 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 feaff84a2..7d8bd4494 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -517,4 +517,30 @@ date: 2025-01-31 versions: 0.72.4.dev seconds_per_case: 124.6 - total_cost: 18.1584 \ No newline at end of file + total_cost: 18.1584 + +- dirname: 2025-01-21-22-51-49--gemini-2.0-flash-thinking-exp-01-21-polyglot-diff + test_cases: 225 + model: gemini-2.0-flash-thinking-exp-01-21 + edit_format: diff + commit_hash: 843720a + pass_rate_1: 5.8 + pass_rate_2: 18.2 + pass_num_1: 13 + pass_num_2: 41 + percent_cases_well_formed: 77.8 + error_outputs: 182 + num_malformed_responses: 180 + num_with_malformed_responses: 50 + user_asks: 26 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 2 + test_timeouts: 7 + total_tests: 225 + command: aider --model gemini/gemini-2.0-flash-thinking-exp-01-21 + date: 2025-01-21 + versions: 0.72.2.dev + seconds_per_case: 24.2 + total_cost: 0.0000 \ No newline at end of file