@article{benchmarkinflationrevealingllmperformanc,
  title = {Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts},
  author = {Jacob Haimes and Cenny Wenner and Kunvar Thaman and Vassil Tashev and Clement Neo and Esben Kran and Jason Schreiber},
  year = {2024},
  eprint = {2410.09247},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.09247v1},
}