mirror of
https://github.com/Aider-AI/aider.git
synced 2025-06-01 18:25:00 +00:00
167 lines
No EOL
4.1 KiB
YAML
167 lines
No EOL
4.1 KiB
YAML
- dirname: 2024-05-04-23-27-02--refac-gemini
|
|
test_cases: 89
|
|
model: gemini/gemini-1.5-pro-latest
|
|
edit_format: diff-fenced
|
|
commit_hash: a0649ba-dirty, 425cb29, 1b35ca2-dirty, 3e4fca2-dirty
|
|
pass_rate_1: 49.4
|
|
percent_cases_well_formed: 7.9
|
|
error_outputs: 247
|
|
num_malformed_responses: 82
|
|
user_asks: 0
|
|
lazy_comments: 4
|
|
syntax_errors: 0
|
|
indentation_errors: 8
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --model gemini/gemini-1.5-pro-latest
|
|
date: 2024-05-04
|
|
versions: 0.31.2-dev
|
|
seconds_per_case: 55.7
|
|
total_cost: 0.0000
|
|
- dirname: 2024-05-04-17-45-53--refac-opus
|
|
test_cases: 83
|
|
model: claude-3-opus-20240229
|
|
edit_format: diff
|
|
commit_hash: b02320b-dirty
|
|
pass_rate_1: 72.3
|
|
percent_cases_well_formed: 79.5
|
|
error_outputs: 51
|
|
num_malformed_responses: 17
|
|
user_asks: 0
|
|
lazy_comments: 2
|
|
syntax_errors: 1
|
|
indentation_errors: 3
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --opus
|
|
date: 2024-05-04
|
|
versions: 0.31.2-dev
|
|
seconds_per_case: 67.8
|
|
total_cost: 27.9176
|
|
- dirname: 2024-04-09-21-49-54--refac-gpt-4-turbo-2024-04-09
|
|
test_cases: 88
|
|
model: gpt-4-turbo-2024-04-09 (udiff)
|
|
edit_format: udiff
|
|
commit_hash: b75fdb9
|
|
pass_rate_1: 34.1
|
|
percent_cases_well_formed: 30.7
|
|
error_outputs: 183
|
|
num_malformed_responses: 61
|
|
user_asks: 0
|
|
lazy_comments: 1
|
|
syntax_errors: 3
|
|
indentation_errors: 15
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --gpt-4-turbo
|
|
date: 2024-04-09
|
|
versions: 0.27.1-dev
|
|
seconds_per_case: 42.4
|
|
total_cost: 19.6556
|
|
|
|
- dirname: 2024-05-08-22-25-41--may-refac-gpt-4-0125-preview-ex-sys
|
|
test_cases: 89
|
|
model: gpt-4-0125-preview
|
|
edit_format: udiff
|
|
commit_hash: bf09bd3-dirty
|
|
pass_rate_1: 33.7
|
|
percent_cases_well_formed: 47.2
|
|
error_outputs: 142
|
|
num_malformed_responses: 47
|
|
user_asks: 0
|
|
lazy_comments: 1
|
|
syntax_errors: 2
|
|
indentation_errors: 16
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --model gpt-4-0125-preview
|
|
date: 2024-05-08
|
|
versions: 0.33.1-dev
|
|
seconds_per_case: 56.6
|
|
total_cost: 20.3270
|
|
|
|
- dirname: 2024-05-08-21-24-16--may-refac-gpt-4-1106-preview
|
|
test_cases: 89
|
|
model: gpt-4-1106-preview
|
|
edit_format: udiff
|
|
commit_hash: eaa2514-dirty
|
|
pass_rate_1: 50.6
|
|
percent_cases_well_formed: 39.3
|
|
error_outputs: 164
|
|
num_malformed_responses: 54
|
|
user_asks: 1
|
|
lazy_comments: 17
|
|
syntax_errors: 0
|
|
indentation_errors: 8
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --model gpt-4-1106-preview
|
|
date: 2024-05-08
|
|
versions: 0.33.1-dev
|
|
seconds_per_case: 61.8
|
|
total_cost: 18.3844
|
|
|
|
- dirname: 2024-05-13-17-42-22--refac-gpt-4o-diff
|
|
test_cases: 89
|
|
model: gpt-4o
|
|
edit_format: diff
|
|
commit_hash: b6cd852
|
|
pass_rate_1: 62.9
|
|
percent_cases_well_formed: 53.9
|
|
error_outputs: 9025
|
|
num_malformed_responses: 41
|
|
user_asks: 0
|
|
lazy_comments: 2
|
|
syntax_errors: 0
|
|
indentation_errors: 5
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider
|
|
date: 2024-05-13
|
|
versions: 0.34.1-dev
|
|
seconds_per_case: 27.8
|
|
total_cost: 0.0000
|
|
|
|
- dirname: 2024-04-10-13-26-18--refac-gpt-4-turbo-2024-04-09-diff
|
|
test_cases: 88
|
|
model: gpt-4-turbo-2024-04-09 (diff)
|
|
edit_format: diff
|
|
commit_hash: 7875418
|
|
pass_rate_1: 21.4
|
|
percent_cases_well_formed: 6.8
|
|
error_outputs: 247
|
|
num_malformed_responses: 82
|
|
user_asks: 1
|
|
lazy_comments: 2
|
|
syntax_errors: 3
|
|
indentation_errors: 8
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --model gpt-4-turbo-2024-04-09
|
|
date: 2024-04-10
|
|
versions: 0.28.1-dev
|
|
seconds_per_case: 67.8
|
|
total_cost: 20.4889
|
|
|
|
|
|
- dirname: 2024-06-20-16-39-18--refac-claude-3.5-sonnet-diff
|
|
test_cases: 89
|
|
model: claude-3.5-sonnet (diff)
|
|
edit_format: diff
|
|
commit_hash: e5e07f9
|
|
pass_rate_1: 55.1
|
|
percent_cases_well_formed: 70.8
|
|
error_outputs: 240
|
|
num_malformed_responses: 54
|
|
num_with_malformed_responses: 26
|
|
user_asks: 10
|
|
lazy_comments: 2
|
|
syntax_errors: 0
|
|
indentation_errors: 3
|
|
exhausted_context_windows: 0
|
|
test_timeouts: 0
|
|
command: aider --model openrouter/anthropic/claude-3.5-sonnet
|
|
date: 2024-06-20
|
|
versions: 0.38.1-dev
|
|
seconds_per_case: 51.9
|
|
total_cost: 0.0000 |