chore: Update edit leaderboard with latest model performance data

This commit is contained in:
Paul Gauthier 2024-10-04 09:35:28 -07:00 committed by Paul Gauthier (aider)
parent af10953534
commit ff230554ce

View file

@ -832,30 +832,6 @@
seconds_per_case: 6.5
total_cost: 0.0000
- dirname: 2024-08-14-13-07-12--chatgpt-4o-latest-diff
test_cases: 133
model: chatgpt-4o-latest
edit_format: diff
commit_hash: b1c3769
pass_rate_1: 53.4
pass_rate_2: 69.2
percent_cases_well_formed: 97.7
error_outputs: 27
num_malformed_responses: 5
num_with_malformed_responses: 3
user_asks: 7
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model openai/chatgpt-4o-latest
date: 2024-08-14
released: 2024-08-08
versions: 0.50.2-dev
seconds_per_case: 26.3
total_cost: 3.6113
- dirname: 2024-08-28-07-10-50--gemini-1.5-pro-exp-0827-diff-fenced
test_cases: 133
model: gemini-1.5-pro-exp-0827
@ -1496,4 +1472,27 @@
date: 2024-10-01
versions: 0.58.1.dev
seconds_per_case: 24.8
total_cost: 0.0000
total_cost: 0.0000
- dirname: 2024-10-04-16-30-08--chatgpt-4o-latest-diff-oct4
test_cases: 133
model: openai/chatgpt-4o-latest
edit_format: diff
commit_hash: af10953
pass_rate_1: 56.4
pass_rate_2: 72.2
percent_cases_well_formed: 97.0
error_outputs: 4
num_malformed_responses: 4
num_with_malformed_responses: 4
user_asks: 21
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openai/chatgpt-4o-latest
date: 2024-10-04
versions: 0.58.2.dev
seconds_per_case: 23.7
total_cost: 4.0641