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)

Sign up or log in to comment