.eval_results/gpqa_diamond.yaml

- dataset:
    id: Idavidrein/gpqa
    task_id: diamond
  value: 83.5
  date: '2026-02-11'
  source:
    url: https://arxiv.org/abs/2602.10604
    name: Step 3.5 Flash Paper
    user: SaylorTwift