This commit is contained in:
Paul Gauthier 2025-04-16 14:58:04 -07:00
parent 24805ff85d
commit efbefc669f
2 changed files with 58 additions and 2 deletions

View file

@ -1081,4 +1081,33 @@
use_repo_map: true
reminder: sys
examples_as_sys_msg: false
- name: o3
edit_format: diff
weak_model_name: gpt-4.1-mini
use_repo_map: true
editor_model_name: gpt-4.1
editor_edit_format: editor-diff
system_prompt_prefix: "Formatting re-enabled. "
accepts_settings: ["reasoning_effort"]
#reminder: sys
examples_as_sys_msg: true
extra_params:
extra_body:
reasoning_effort: high
- name: o4-mini
edit_format: diff
weak_model_name: gpt-4.1-mini
use_repo_map: true
use_temperature: false
editor_model_name: gpt-4.1
editor_edit_format: editor-diff
system_prompt_prefix: "Formatting re-enabled. "
accepts_settings: ["reasoning_effort"]
#reminder: sys
#examples_as_sys_msg: false
extra_params:
extra_body:
reasoning_effort: low

View file

@ -1091,4 +1091,31 @@
date: 2025-04-14
versions: 0.81.4.dev
seconds_per_case: 12.0
total_cost: 0.4281
total_cost: 0.4281
- dirname: 2025-04-16-21-20-55--o3-high-diff-temp0-exsys
test_cases: 225
model: o3
edit_format: diff
commit_hash: 24805ff-dirty
pass_rate_1: 36.9
pass_rate_2: 79.6
pass_num_1: 83
pass_num_2: 179
percent_cases_well_formed: 95.1
error_outputs: 11
num_malformed_responses: 11
num_with_malformed_responses: 11
user_asks: 110
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
total_tests: 225
command: aider --model o3
date: 2025-04-16
versions: 0.82.1.dev
seconds_per_case: 113.8
total_cost: 111.0325