- dataset:
    id: TIGER-Lab/MMLU-Pro
    task_id: mmlu_pro
  value: 88.12
  date: '2026-09-28'
  source:
    url: https://huggingface.co/FINAL-Bench/Darwin-180B-RSI
    name: Model Card
  notes: "MMLU-Pro test, all 12,032 items; single sample (temperature=1.0, top_p=0.95, top_k=20); thinking budget 131,072 tokens; bf16"