- dataset:
    id: MathArena/apex_2025
    task_id: MathArena/apex_2025
  value: 89.6
  source:
    url: https://huggingface.co/datasets/tsinghua-sigs-robot-lab/VeriLoop-E2-Evaluation-Evidence/tree/main/apex-2025
    name: VeriLoop E2 Evaluation Evidence