- dataset:
    id: ScaleAI/SWE-bench_Pro
    task_id: SWE_Bench_Pro
  value: 76.2
  source:
    url: https://huggingface.co/datasets/tsinghua-sigs-robot-lab/VeriLoop-E2-Evaluation-Evidence/tree/main/swe-bench-pro
    name: VeriLoop E2 Evaluation Evidence