@article{dolargelanguagemodelbenchmarkstest,
  title = {Do Large Language Model Benchmarks Test Reliability?},
  author = {Joshua Vendrow and Edward Vendrow and Sara Beery and Aleksander Madry},
  year = {2025},
  eprint = {2502.03461},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.03461v1},
}