o1-mini diff results

This commit is contained in:
Paul Gauthier 2024-09-12 15:38:40 -07:00
parent 1fbb5079d5
commit c00ac80909
3 changed files with 68 additions and 17 deletions

View file

@ -1089,7 +1089,7 @@
- dirname: 2024-09-12-19-57-35--o1-mini-whole
test_cases: 133
model: o1-mini
model: o1-mini (whole)
edit_format: whole
commit_hash: 36fa773-dirty, 291b456
pass_rate_1: 49.6
@ -1108,4 +1108,28 @@
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 103.0
total_cost: 5.3725
total_cost: 5.3725
- dirname: 2024-09-12-20-56-22--o1-mini-diff
test_cases: 133
model: o1-mini (diff)
edit_format: diff
commit_hash: 4598a37-dirty, 291b456, 752e823-dirty
pass_rate_1: 45.1
pass_rate_2: 62.4
percent_cases_well_formed: 85.7
error_outputs: 26
num_malformed_responses: 26
num_with_malformed_responses: 19
user_asks: 2
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini --edit-format diff
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 177.7
total_cost: 11.1071

View file

@ -91,4 +91,28 @@
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 103.0
total_cost: 5.3725
total_cost: 5.3725
- dirname: 2024-09-12-20-56-22--o1-mini-diff
test_cases: 133
model: o1-mini (diff)
edit_format: diff
commit_hash: 4598a37-dirty, 291b456, 752e823-dirty
pass_rate_1: 45.1
pass_rate_2: 62.4
percent_cases_well_formed: 85.7
error_outputs: 26
num_malformed_responses: 26
num_with_malformed_responses: 19
user_asks: 2
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini --edit-format diff
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 177.7
total_cost: 11.1071