.eval_results/mmlu_pro.yaml

- dataset:
    id: TIGER-Lab/MMLU-Pro
    task_id: mmlu_pro
  value: 84.4
  date: '2026-02-11'
  source:
    url: https://arxiv.org/abs/2602.10604
    name: Step 3.5 Flash Paper
    user: SaylorTwift