81.2% on Aider Ployglot!!
#2
by
Fernanda24
- opened
vllm bf16 default settings 224/225
- dirname: 2025-08-02-07-20-13--MindLink-32B-0801
test_cases: 224
model: openai/MindLink-32B-0801
edit_format: diff
commit_hash: f38200c
pass_rate_1: 34.4
pass_rate_2: 81.2
pass_num_1: 77
pass_num_2: 182
percent_cases_well_formed: 92.9
error_outputs: 29
num_malformed_responses: 26
num_with_malformed_responses: 16
user_asks: 97
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 3
prompt_tokens: 2732578
completion_tokens: 327592
test_timeouts: 2
total_tests: 225
command: aider --model openai/MindLink-32B-0801
date: 2025-08-02
versions: 0.85.3.dev
seconds_per_case: 232.7
-----------|-------|-------|-------|-------|-------|-------|-----------
python | 29.4 | 91.2 | 10 | 31 | 34 | 1 | 1
javascript | 41.7 | 83.3 | 20 | 40 | 48 | 0 | 2
java | 36.2 | 68.1 | 17 | 32 | 47 | 6 | 14
cpp | 15.4 | 88.5 | 4 | 23 | 26 | 87 | 1
go | 35.9 | 84.6 | 14 | 33 | 39 | 3 | 4
rust | 40.0 | 76.7 | 12 | 23 | 30 | 0 | 4
This comment has been hidden (marked as Resolved)