@article{beyondtheleaderboardrethinkingmedicalben, title = {Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models}, author = {Wenting Chen and Guo Yu and Yiu-Fai Cheung and Meidan Ding and Jie Liu and Zizhan Ma and Wenxuan Wang and Linlin Shen}, year = {2025}, eprint = {2508.04325}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04325}, }