@article{medagentsbenchbenchmarkingthinkingmodels,
  title = {MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning},
  author = {Xiangru Tang and Daniel Shao and Jiwoong Sohn and Jiapeng Chen and Jiayi Zhang and Jinyu Xiang and Fang Wu and Yilun Zhao and Chenglin Wu and Wenqi Shi and Arman Cohan and Mark Gerstein},
  year = {2025},
  eprint = {2503.07459},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.07459v1},
}