@article{medcalcbenchevaluatinglargelanguage,
  title = {MedCalc-Bench: Evaluating Large Language Models for Medical Calculations},
  author = {Nikhil Khandekar and Qiao Jin and Guangzhi Xiong and Soren Dunn and Serina S Applebaum and Zain Anwar and Maame Sarfo-Gyamfi and Conrad W Safranek and Abid A Anwar and Andrew Zhang and Aidan Gilson and Maxwell B Singer and Amisha Dave and Andrew Taylor and Aidong Zhang and Qingyu Chen and Zhiyong Lu},
  year = {2024},
  eprint = {2406.12036},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.12036v4},
}