@article{healthbenchevaluatinglargelanguagemodels,
  title = {HealthBench: Evaluating Large Language Models Towards Improved Human Health},
  author = {Rahul K. Arora and Jason Wei and Rebecca Soskin Hicks and Preston Bowman and Joaquin Quiñonero-Candela and Foivos Tsimpourlas and Michael Sharman and Meghan Shah and Andrea Vallone and Alex Beutel and Johannes Heidecke and Karan Singhal},
  year = {2025},
  eprint = {2505.08775},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.08775v1},
}