@article{kokushimd10benchmarkforevaluatinglarge,
  title = {KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations},
  author = {Junyu Liu and Kaiqi Yan and Tianyang Wang and Qian Niu and Momoko Nagai-Tanima and Tomoki Aoyama},
  year = {2025},
  eprint = {2506.11114},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.11114v1},
}