.eval_results/gpqa.yaml

- dataset:
    id: Idavidrein/gpqa
    task_id: diamond
  value: 85.2
  date: '2026-02-13'
  source:
    url: https://huggingface.co/MiniMaxAI/MiniMax-M2.5
    name: Model Card
    user: SaylorTwift