dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-31 09:44:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

chore: Update polyglot leaderboard with Qwen Max test results

Browse source
This commit is contained in:
Paul Gauthier 2025-01-30 08:38:28 -08:00 • committed by Paul Gauthier (aider)
parent d743c196be
commit 01d0e13884
1 changed files with 25 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

25
aider/website/_data/polyglot_leaderboard.yml
View file

@ -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