@article{benchmarkagreementtestingdonerighta,
  title = {Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench},
  author = {Yotam Perlitz and Ariel Gera and Ofir Arviv and Asaf Yehudai and Elron Bandel and Eyal Shnarch and Michal Shmueli-Scheuer and Leshem Choshen},
  year = {2024},
  eprint = {2407.13696},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.13696v2},
}