o1-mini blog article

This commit is contained in:
Paul Gauthier 2024-09-12 14:07:06 -07:00
parent 291b456a45
commit 96587f5f46
3 changed files with 181 additions and 1 deletions

View file

@ -0,0 +1,94 @@
- dirname: 2024-07-18-18-57-46--gpt-4o-mini-whole
test_cases: 133
model: gpt-4o-mini
edit_format: whole
commit_hash: d31eef3-dirty
pass_rate_1: 40.6
pass_rate_2: 55.6
released: 2024-07-18
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model gpt-4o-mini
date: 2024-07-18
versions: 0.44.1-dev
seconds_per_case: 7.8
total_cost: 0.0916
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
test_cases: 133
model: claude-3.5-sonnet
edit_format: diff
commit_hash: 35f21b5
pass_rate_1: 57.1
pass_rate_2: 77.4
percent_cases_well_formed: 99.2
error_outputs: 23
released: 2024-06-20
num_malformed_responses: 4
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --sonnet
date: 2024-07-04
versions: 0.42.1-dev
seconds_per_case: 17.6
total_cost: 3.6346
- dirname: 2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again
test_cases: 133
model: gpt-4o-2024-08-06
edit_format: diff
commit_hash: ed9ed89
pass_rate_1: 57.1
pass_rate_2: 71.4
percent_cases_well_formed: 98.5
error_outputs: 18
num_malformed_responses: 2
num_with_malformed_responses: 2
user_asks: 10
lazy_comments: 0
syntax_errors: 6
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 5
released: 2024-08-06
command: aider --model openai/gpt-4o-2024-08-06
date: 2024-08-06
versions: 0.48.1-dev
seconds_per_case: 6.5
total_cost: 0.0000
- dirname: 2024-09-12-19-57-35--o1-mini-whole
test_cases: 133
model: o1-mini
edit_format: whole
commit_hash: 36fa773-dirty, 291b456
pass_rate_1: 49.6
pass_rate_2: 70.7
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 17
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openai/o1-mini
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 103.0
total_cost: 5.3725