dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-01 10:14:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

chore: Update polyglot leaderboard with new test run data

Browse source
This commit is contained in:
Paul Gauthier 2025-01-31 15:13:34 -08:00 • committed by Paul Gauthier (aider)
parent 061b602334
commit 1a6a16e061
1 changed files with 27 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

28
aider/website/_data/polyglot_leaderboard.yml
View file

@ -517,4 +517,30 @@
date: 2025-01-31 date: 2025-01-31
versions: 0.72.4.dev versions: 0.72.4.dev
seconds_per_case: 124.6 seconds_per_case: 124.6
total_cost: 18.1584 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