From 114a0e5ab9ec833ea5e6160e5a8b744ae0aa98db Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 8 May 2025 06:42:12 -0700 Subject: [PATCH] feat: Add qwen3 leaderboard data for 32b and 235b models --- aider/website/_data/polyglot_leaderboard.yml | 58 +++++++++++++++++++- 1 file changed, 57 insertions(+), 1 deletion(-) diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index ded7cefcb..3d19d7685 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -1249,4 +1249,60 @@ date: 2025-05-07 versions: 0.82.4.dev seconds_per_case: 165.3 - total_cost: 37.4104 \ No newline at end of file + total_cost: 37.4104 + +- dirname: 2025-05-08-03-20-24--qwen3-32b-default + test_cases: 225 + model: openrouter/qwen/qwen3-32b + edit_format: diff + commit_hash: aaacee5-dirty, aeaf259 + pass_rate_1: 14.2 + pass_rate_2: 40.0 + pass_num_1: 32 + pass_num_2: 90 + percent_cases_well_formed: 83.6 + error_outputs: 119 + num_malformed_responses: 50 + num_with_malformed_responses: 37 + user_asks: 97 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 12 + prompt_tokens: 317591 + completion_tokens: 120418 + test_timeouts: 5 + total_tests: 225 + command: aider --model openrouter/qwen/qwen3-32b + date: 2025-05-08 + versions: 0.82.4.dev + seconds_per_case: 372.2 + total_cost: 0.7603 + +- dirname: 2025-05-08-03-22-37--qwen3-235b-defaults + test_cases: 225 + model: openrouter/qwen/qwen3-235b-a22b + edit_format: diff + commit_hash: aaacee5-dirty + pass_rate_1: 17.3 + pass_rate_2: 49.8 + pass_num_1: 39 + pass_num_2: 112 + percent_cases_well_formed: 91.6 + error_outputs: 58 + num_malformed_responses: 29 + num_with_malformed_responses: 19 + user_asks: 102 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 0 + prompt_tokens: 0 + completion_tokens: 0 + test_timeouts: 1 + total_tests: 225 + command: aider --model openrouter/qwen/qwen3-235b-a22b + date: 2025-05-08 + versions: 0.82.4.dev + seconds_per_case: 428.1 + total_cost: 1.8037 \ No newline at end of file