- dataset:
    id: openai/gsm8k
    task_id: gsm8k
  value: 85.22
  date: "2026-05-10"
  source:
    url: https://huggingface.co/hadadxyz/OpenSonnet-Lite-MAX
    name: Model Card
    user: hadadxyz
  notes: |
    framework: lm-evaluation-harness
    n-shot: 8
    batch_size: 1
    generation_kwargs:
      num_ctx: 262144
      max_tokens: 131072
      temperature: 0.6
      top_p: 0.95
      top_k: 20
      min_p: 0
      repeat_penalty: 1.0
      presence_penalty: 1.0
    metric: exact_match
    match_type: strict-match