dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-06 04:35:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

chore: Update polyglot leaderboard test results and metadata

Browse source
This commit is contained in:
Paul Gauthier 2025-01-17 13:37:02 -08:00 • committed by Paul Gauthier (aider)
parent 5b6c186125
commit a777f336e1
1 changed files with 17 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

32
aider/website/_data/polyglot_leaderboard.yml
View file

@ -24,31 +24,31 @@
seconds_per_case: 17.3 seconds_per_case: 17.3
total_cost: 0.3236 total_cost: 0.3236
- dirname: 2024-12-21-18-44-28--polyglot-sonnet - dirname: 2025-01-17-19-44-33--sonnet-baseline-jan-17
test_cases: 225 test_cases: 225
model: claude-3-5-sonnet-20241022 model: claude-3-5-sonnet-20241022
edit_format: diff edit_format: diff
commit_hash: a755079-dirty commit_hash: 6451d59
pass_rate_1: 18.7 pass_rate_1: 22.2
pass_rate_2: 45.3 pass_rate_2: 51.6
pass_num_1: 42 pass_num_1: 50
pass_num_2: 102 pass_num_2: 116
percent_cases_well_formed: 100.0 percent_cases_well_formed: 99.6
error_outputs: 1 error_outputs: 2
num_malformed_responses: 0 num_malformed_responses: 1
num_with_malformed_responses: 0 num_with_malformed_responses: 1
user_asks: 14 user_asks: 11
lazy_comments: 0 lazy_comments: 0
syntax_errors: 0 syntax_errors: 0
indentation_errors: 0 indentation_errors: 0
exhausted_context_windows: 1 exhausted_context_windows: 1
test_timeouts: 12 test_timeouts: 8
total_tests: 225 total_tests: 225
command: aider --model claude-3-5-sonnet-20241022 command: aider --model claude-3-5-sonnet-20241022
date: 2024-12-21 date: 2025-01-17
versions: 0.69.2.dev versions: 0.71.2.dev
seconds_per_case: 30.8 seconds_per_case: 21.4
total_cost: 13.4847 total_cost: 14.4063
- dirname: 2024-12-30-20-57-12--gpt-4o-2024-11-20-ex-as-sys - dirname: 2024-12-30-20-57-12--gpt-4o-2024-11-20-ex-as-sys
test_cases: 225 test_cases: 225