From 01d0e13884c111281439687a47f1cdff4c6febfb Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 30 Jan 2025 08:38:28 -0800 Subject: [PATCH] chore: Update polyglot leaderboard with Qwen Max test results --- aider/website/_data/polyglot_leaderboard.yml | 25 ++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index c3566e75a..0fac32c7a 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -441,3 +441,28 @@ versions: 0.72.3.dev seconds_per_case: 251.6 total_cost: 13.2933 + +- dirname: 2025-01-28-16-00-03--qwen-max-2025-01-25-polyglot-diff + test_cases: 225 + model: Qwen Max + edit_format: diff + commit_hash: ae7d459 + pass_rate_1: 9.3 + pass_rate_2: 21.8 + pass_num_1: 21 + pass_num_2: 49 + percent_cases_well_formed: 90.2 + error_outputs: 46 + num_malformed_responses: 44 + num_with_malformed_responses: 22 + user_asks: 23 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 0 + test_timeouts: 9 + total_tests: 225 + command: OPENAI_API_BASE=https://dashscope-intl.aliyuncs.com/compatible-mode/v1 aider --model openai/qwen-max-2025-01-25 + date: 2025-01-28 + versions: 0.72.4.dev + seconds_per_case: 39.5