mirror of
https://github.com/Aider-AI/aider.git
synced 2025-06-01 18:25:00 +00:00
added claude-3-5-sonnet-20241022 benchmarks
This commit is contained in:
parent
ae54ef57ae
commit
cfcb6656cb
1 changed files with 25 additions and 2 deletions
|
@ -547,7 +547,7 @@
|
||||||
|
|
||||||
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
|
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
|
||||||
test_cases: 133
|
test_cases: 133
|
||||||
model: claude-3.5-sonnet
|
model: claude-3.5-sonnet-20240620
|
||||||
edit_format: diff
|
edit_format: diff
|
||||||
commit_hash: 35f21b5
|
commit_hash: 35f21b5
|
||||||
pass_rate_1: 57.1
|
pass_rate_1: 57.1
|
||||||
|
@ -563,7 +563,7 @@
|
||||||
indentation_errors: 0
|
indentation_errors: 0
|
||||||
exhausted_context_windows: 0
|
exhausted_context_windows: 0
|
||||||
test_timeouts: 1
|
test_timeouts: 1
|
||||||
command: aider --sonnet
|
command: aider --model claude-3.5-sonnet-20240620
|
||||||
date: 2024-07-04
|
date: 2024-07-04
|
||||||
versions: 0.42.1-dev
|
versions: 0.42.1-dev
|
||||||
seconds_per_case: 17.6
|
seconds_per_case: 17.6
|
||||||
|
@ -1587,4 +1587,27 @@
|
||||||
date: 2024-10-16
|
date: 2024-10-16
|
||||||
versions: 0.59.2.dev
|
versions: 0.59.2.dev
|
||||||
seconds_per_case: 64.9
|
seconds_per_case: 64.9
|
||||||
|
total_cost: 0.0000
|
||||||
|
|
||||||
|
- dirname: 2024-10-22-16-18-20--sonnet-1022-diff
|
||||||
|
test_cases: 133
|
||||||
|
model: claude-3-5-sonnet-20241022
|
||||||
|
edit_format: diff
|
||||||
|
commit_hash: 46269f2-dirty
|
||||||
|
pass_rate_1: 67.7
|
||||||
|
pass_rate_2: 83.5
|
||||||
|
percent_cases_well_formed: 98.5
|
||||||
|
error_outputs: 5
|
||||||
|
num_malformed_responses: 5
|
||||||
|
num_with_malformed_responses: 2
|
||||||
|
user_asks: 2
|
||||||
|
lazy_comments: 1
|
||||||
|
syntax_errors: 0
|
||||||
|
indentation_errors: 0
|
||||||
|
exhausted_context_windows: 0
|
||||||
|
test_timeouts: 1
|
||||||
|
command: aider --model anthropic/claude-3-5-sonnet-20241022
|
||||||
|
date: 2024-10-22
|
||||||
|
versions: 0.59.2.dev
|
||||||
|
seconds_per_case: 17.7
|
||||||
total_cost: 0.0000
|
total_cost: 0.0000
|
Loading…
Add table
Add a link
Reference in a new issue