model_name: "Qwen/Qwen3.5-397B-A17B"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.9704
  - name: "exact_match,flexible-extract"
    value: 0.9697
limit: 1319
num_concurrent: 256
num_fewshot: 5
gen_kwargs: "max_gen_toks=2048"
rtol: 0.05