@article{easy2hardbenchstandardizeddifficulty,
  title = {Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization},
  author = {Mucong Ding and ChengHao Deng and Jocelyn Choo and Zichu Wu and Aakriti Agrawal and Avi Schwarzschild and Tianyi Zhou and Tom Goldstein and John Langford and Anima Anandkumar and Furong Huang},
  year = {2024},
  eprint = {2409.18433},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.18433v1},
}