This commit is contained in:
Paul Gauthier 2025-05-08 06:41:36 -07:00
parent 1d2818a064
commit 71338a679e

View file

@ -1225,55 +1225,3 @@
seconds_per_case: 50.1
total_cost: 1.8451
- dirname: 2025-05-07-22-39-51--qwen3-235b-high
test_cases: 225
model: Qwen3 235B A22B (high)
edit_format: diff
commit_hash: eabc98b-dirty
pass_rate_1: 18.2
pass_rate_2: 48.0
pass_num_1: 41
pass_num_2: 108
percent_cases_well_formed: 87.1
error_outputs: 68
num_malformed_responses: 43
num_with_malformed_responses: 29
user_asks: 89
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
total_tests: 225
command: aider --model openrouter/qwen/qwen3-235b-a22b --reasoning-effort high
date: 2025-05-07
versions: 0.82.4.dev
seconds_per_case: 477.5
total_cost: 0.0000
- dirname: 2025-05-07-23-12-42--qwen3-32b-high
test_cases: 225
model: Qwen3 32B (high)
edit_format: diff
commit_hash: c756b08-dirty
reasoning_effort: high
pass_rate_1: 16.0
pass_rate_2: 36.4
pass_num_1: 36
pass_num_2: 82
percent_cases_well_formed: 82.2
error_outputs: 73
num_malformed_responses: 52
num_with_malformed_responses: 40
user_asks: 99
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 2
test_timeouts: 5
total_tests: 225
command: aider --model openrouter/qwen/qwen3-32b --reasoning-effort high
date: 2025-05-07
versions: 0.82.4.dev
seconds_per_case: 364.7
total_cost: 0.0000