.eval_results/aime_2026.yaml

- dataset:
    id: MathArena/aime_2026
    task_id: MathArena/aime_2026
  value: 95.1
  date: '2026-04-23'
  source:
    url: https://huggingface.co/OrionLLM/GRM-2.6-Plus
    name: Official GRM-2.6 Benchmark
    user: DedeProGames