dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-02 18:54:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

chore: Add new polyglot benchmark results

Browse source
This commit is contained in:
Paul Gauthier 2025-05-26 08:56:01 -07:00 • committed by Paul Gauthier (aider)
parent 3194a35230
commit 214b811ef9
1 changed files with 30 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

31
aider/website/_data/polyglot_leaderboard.yml
View file

@ -1447,4 +1447,33 @@
date: 2025-05-25 date: 2025-05-25
versions: 0.83.3.dev versions: 0.83.3.dev
seconds_per_case: 50.4 seconds_per_case: 50.4
total_cost: 7.6091 total_cost: 7.6091
- dirname: 2025-05-25-22-58-44--flash25-05-20-24k-think
test_cases: 225
model: gemini/gemini-2.5-flash-preview-05-20
edit_format: diff
commit_hash: a8568c3-dirty
thinking_tokens: 24576
pass_rate_1: 26.2
pass_rate_2: 55.1
pass_num_1: 59
pass_num_2: 124
percent_cases_well_formed: 95.6
error_outputs: 15
num_malformed_responses: 15
num_with_malformed_responses: 10
user_asks: 101
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
prompt_tokens: 3666792
completion_tokens: 2703162
test_timeouts: 4
total_tests: 225
command: aider --model gemini/gemini-2.5-flash-preview-05-20
date: 2025-05-25
versions: 0.83.3.dev
seconds_per_case: 53.9
total_cost: 8.5625