@article{equibenchbenchmarkingcodereasoning,
  title = {EquiBench: Benchmarking Large Language Models' Understanding of Program Semantics via Equivalence Checking},
  author = {Anjiang Wei and Jiannan Cao and Ran Li and Hongyu Chen and Yuhui Zhang and Ziheng Wang and YuAn Liu and Thiago S. F. X. Teixeira and Diyi Yang and Ke Wang and Alex Aiken},
  year = {2025},
  eprint = {2502.12466},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.12466v2},
}