From e8a8681a7506c366b6e3079e16969dd021ae0eda Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 13 Mar 2025 14:16:20 -0700 Subject: [PATCH] chore: Update polyglot leaderboard YAML files with new test case data --- .../website/_data/o1_polyglot_leaderboard.yml | 2 +- aider/website/_data/polyglot_leaderboard.yml | 28 ++++++++++++++++++- 2 files changed, 28 insertions(+), 2 deletions(-) diff --git a/aider/website/_data/o1_polyglot_leaderboard.yml b/aider/website/_data/o1_polyglot_leaderboard.yml index 20e8102ad..f8c0dad14 100644 --- a/aider/website/_data/o1_polyglot_leaderboard.yml +++ b/aider/website/_data/o1_polyglot_leaderboard.yml @@ -256,4 +256,4 @@ date: 2024-12-22 versions: 0.69.2.dev seconds_per_case: 12.2 - total_cost: 0.0000 \ No newline at end of file + total_cost: 0.0000 diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index 715f94cdb..486167a55 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -727,4 +727,30 @@ date: 2025-03-07 versions: 0.75.3.dev seconds_per_case: 137.4 - total_cost: 0 \ No newline at end of file + total_cost: 0 + +- dirname: 2025-03-13-20-46-30--cmda-whole + test_cases: 225 + model: command-a-03-2025 + edit_format: whole + commit_hash: 024b913-dirty + pass_rate_1: 2.2 + pass_rate_2: 4.9 + pass_num_1: 5 + pass_num_2: 11 + percent_cases_well_formed: 100.0 + error_outputs: 38 + num_malformed_responses: 0 + num_with_malformed_responses: 0 + user_asks: 231 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 0 + test_timeouts: 2 + total_tests: 225 + command: aider --model cohere_chat/command-a-03-2025 + date: 2025-03-13 + versions: 0.76.3.dev + seconds_per_case: 106.3 + total_cost: 0.0000 \ No newline at end of file