{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T11:10:04Z","timestamp":1790161804795,"version":"4.1.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":61,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32270690"],"award-info":[{"award-number":["32270690"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Provincial Science and Technology Support Program","doi-asserted-by":"publisher","award":["2024YFHZ0205"],"award-info":[{"award-number":["2024YFHZ0205"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-026-07261-9","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T12:26:55Z","timestamp":1776428815000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Dataset for Evaluating Large Language Models on Chinese National Medical Licensing Examinations"],"prefix":"10.1038","volume":"13","author":[{"given":"Hui","family":"Zong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxue","family":"Cha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muyun","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-1531","authenticated-orcid":false,"given":"Bairong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"10377","key":"7261_CR1","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/S0140-6736(23)00216-7","volume":"401","author":"A Arora","year":"2023","unstructured":"Arora, A. & Arora, A. The promise of large language models in health care. Lancet. 401(10377), 641, https:\/\/doi.org\/10.1016\/S0140-6736(23)00216-7 (2023).","journal-title":"Lancet."},{"issue":"1","key":"7261_CR2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","volume":"3","author":"J Clusmann","year":"2023","unstructured":"Clusmann, J. et al. The future landscape of large language models in medicine. Commun Med (Lond) 3(1), 141, https:\/\/doi.org\/10.1038\/s43856-023-00370-1 (2023).","journal-title":"Commun Med (Lond)"},{"issue":"8","key":"7261_CR3","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A. J. et al. Large language models in medicine. Nat Med. 29(8), 1930\u201340, https:\/\/doi.org\/10.1038\/s41591-023-02448-8 (2023).","journal-title":"Nat Med."},{"issue":"9","key":"7261_CR4","doi-asserted-by":"publisher","first-page":"1801","DOI":"10.1093\/jamia\/ocae202","volume":"31","author":"Z Lu","year":"2024","unstructured":"Lu, Z. et al. Large language models in biomedicine and health: current research landscape and future directions. J Am Med Inform Assoc. 31(9), 1801\u201311, https:\/\/doi.org\/10.1093\/jamia\/ocae202 (2024).","journal-title":"J Am Med Inform Assoc."},{"key":"7261_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104716","volume":"157","author":"H Zong","year":"2024","unstructured":"Zong, H. et al. Advancing Chinese biomedical text mining with community challenges. J Biomed Inform. 157, 104716, https:\/\/doi.org\/10.1016\/j.jbi.2024.104716 (2024).","journal-title":"J Biomed Inform."},{"issue":"2","key":"7261_CR6","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1097\/ACM.0000000000005937","volume":"100","author":"A Rodman","year":"2025","unstructured":"Rodman, A., Mark, N. M., Artino, A. R. Jr. & Lessing, J. N. Using Generative Artificial Intelligence in Medical Education. Acad Med. 100(2), 250, https:\/\/doi.org\/10.1097\/ACM.0000000000005937 (2025).","journal-title":"Acad Med."},{"issue":"1","key":"7261_CR7","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-05738-y","volume":"24","author":"J Li","year":"2024","unstructured":"Li, J. et al. Exploring the potential of artificial intelligence to enhance the writing of english academic papers by non-native english-speaking medical students - the educational application of ChatGPT. BMC Med Educ. 24(1), 736, https:\/\/doi.org\/10.1186\/s12909-024-05738-y (2024).","journal-title":"BMC Med Educ."},{"key":"7261_CR8","doi-asserted-by":"publisher","first-page":"e48291","DOI":"10.2196\/48291","volume":"9","author":"A Abd-Alrazaq","year":"2023","unstructured":"Abd-Alrazaq, A. et al. Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions. JMIR Med Educ. 9, e48291, https:\/\/doi.org\/10.2196\/48291 (2023).","journal-title":"JMIR Med Educ."},{"issue":"7972","key":"7261_CR9","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature. 620(7972), 172\u201380, https:\/\/doi.org\/10.1038\/s41586-023-06291-2 (2023).","journal-title":"Nature."},{"key":"7261_CR10","doi-asserted-by":"publisher","unstructured":"Sandmann, S. et al. Benchmark evaluation of DeepSeek large language models in clinical decision-making. Nat Med. https:\/\/doi.org\/10.1038\/s41591-025-03727-2 (2025).","DOI":"10.1038\/s41591-025-03727-2"},{"issue":"9","key":"7261_CR11","doi-asserted-by":"publisher","first-page":"1884","DOI":"10.1093\/jamia\/ocae184","volume":"31","author":"J Zhang","year":"2024","unstructured":"Zhang, J. et al. The potential and pitfalls of using a large language model such as ChatGPT, GPT-4, or LLaMA as a clinical assistant. J Am Med Inform Assoc. 31(9), 1884\u201391, https:\/\/doi.org\/10.1093\/jamia\/ocae184 (2024).","journal-title":"J Am Med Inform Assoc."},{"issue":"1","key":"7261_CR12","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41746-024-01233-2","volume":"7","author":"IC Wiest","year":"2024","unstructured":"Wiest, I. C. et al. Privacy-preserving large language models for structured medical information retrieval. NPJ Digit Med. 7(1), 257, https:\/\/doi.org\/10.1038\/s41746-024-01233-2 (2024).","journal-title":"NPJ Digit Med."},{"key":"7261_CR13","doi-asserted-by":"publisher","first-page":"e67677","DOI":"10.2196\/67677","volume":"27","author":"Y Hou","year":"2025","unstructured":"Hou, Y., Bishop, J. R., Liu, H. & Zhang, R. Improving Dietary Supplement Information Retrieval: Development of a Retrieval-Augmented Generation System With Large Language Models. J Med Internet Res. 27, e67677, https:\/\/doi.org\/10.2196\/67677 (2025).","journal-title":"J Med Internet Res."},{"issue":"5","key":"7261_CR14","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1093\/jamia\/ocaf050","volume":"32","author":"R Sanghera","year":"2025","unstructured":"Sanghera, R. et al. High-performance automated abstract screening with large language model ensembles. J Am Med Inform Assoc. 32(5), 893\u2013904, https:\/\/doi.org\/10.1093\/jamia\/ocaf050 (2025).","journal-title":"J Am Med Inform Assoc."},{"key":"7261_CR15","doi-asserted-by":"publisher","first-page":"e66114","DOI":"10.2196\/66114","volume":"26","author":"H Zong","year":"2024","unstructured":"Zong, H. et al. Large Language Models in Worldwide Medical Exams: Platform Development and Comprehensive Analysis. J Med Internet Res. 26, e66114, https:\/\/doi.org\/10.2196\/66114 (2024).","journal-title":"J Med Internet Res."},{"key":"7261_CR16","doi-asserted-by":"publisher","first-page":"e60807","DOI":"10.2196\/60807","volume":"26","author":"M Liu","year":"2024","unstructured":"Liu, M. et al. Performance of ChatGPT Across Different Versions in Medical Licensing Examinations Worldwide: Systematic Review and Meta-Analysis. J Med Internet Res. 26, e60807, https:\/\/doi.org\/10.2196\/60807 (2024).","journal-title":"J Med Internet Res."},{"issue":"2","key":"7261_CR17","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung, T. H. et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit Health. 2(2), e0000198, https:\/\/doi.org\/10.1371\/journal.pdig.0000198 (2023).","journal-title":"PLOS Digit Health."},{"key":"7261_CR18","doi-asserted-by":"publisher","first-page":"e54393","DOI":"10.2196\/54393","volume":"10","author":"T Nakao","year":"2024","unstructured":"Nakao, T. et al. Capability of GPT-4V(ision) in the Japanese National Medical Licensing Examination: Evaluation Study. JMIR Med Educ. 10, e54393, https:\/\/doi.org\/10.2196\/54393 (2024).","journal-title":"JMIR Med Educ."},{"issue":"1","key":"7261_CR19","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-05125-7","volume":"24","author":"H Zong","year":"2024","unstructured":"Zong, H. et al. Performance of ChatGPT on Chinese national medical licensing examinations: a five-year examination evaluation study for physicians, pharmacists and nurses. BMC Med Educ. 24(1), 143, https:\/\/doi.org\/10.1186\/s12909-024-05125-7 (2024).","journal-title":"BMC Med Educ."},{"issue":"1","key":"7261_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98949-2","volume":"15","author":"D Luo","year":"2025","unstructured":"Luo, D. et al. Evaluating the performance of GPT-3.5, GPT-4, and GPT-4o in the Chinese National Medical Licensing Examination. Sci Rep. 15(1), 14119, https:\/\/doi.org\/10.1038\/s41598-025-98949-2 (2025).","journal-title":"Sci Rep."},{"issue":"1190","key":"7261_CR21","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1093\/postmj\/qgae062","volume":"100","author":"L Huang","year":"2024","unstructured":"Huang, L. et al. The performance evaluation of artificial intelligence ERNIE bot in Chinese National Medical Licensing Examination. Postgrad Med J. 100(1190), 952\u20133, https:\/\/doi.org\/10.1093\/postmj\/qgae062 (2024).","journal-title":"Postgrad Med J."},{"key":"7261_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105173","volume":"177","author":"H Wang","year":"2023","unstructured":"Wang, H., Wu, W., Dou, Z., He, L. & Yang, L. Performance and exploration of ChatGPT in medical examination, records and education in Chinese: Pave the way for medical AI. Int J Med Inform. 177, 105173, https:\/\/doi.org\/10.1016\/j.ijmedinf.2023.105173 (2023).","journal-title":"Int J Med Inform."},{"key":"7261_CR23","doi-asserted-by":"publisher","DOI":"10.1177\/20552076231184091","volume":"9","author":"Z Zhu","year":"2023","unstructured":"Zhu, Z., Ying, Y., Zhu, J. & Wu, H. ChatGPT\u2019s potential role in non-English-speaking outpatient clinic settings. Digit Health. 9, 20552076231184091, https:\/\/doi.org\/10.1177\/20552076231184091 (2023).","journal-title":"Digit Health."},{"key":"7261_CR24","doi-asserted-by":"crossref","unstructured":"Grzybowski, \u0141., Pokrywka, J., Ciesi\u00f3\u0142ka, M., Kaczmarek, J. I. & Kubis M. Polish-English medical knowledge transfer: A newbenchmark and results. In: Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9042\u20139063, Suzhou, China. Association for Computational Linguistics (2025).","DOI":"10.18653\/v1\/2025.findings-emnlp.480"},{"key":"7261_CR25","doi-asserted-by":"publisher","unstructured":"Carrillo-Larco, R. M., Melgarejo, J. L., Castillo-Cara, M. & Bravo-Rocca, G. PeruMedQA: Benchmarking Large Language Models LLMs) on Peruvian Medical Exams\u2014Dataset Construction and Evaluation. Med. Sci. Educ. https:\/\/doi.org\/10.1007\/s40670-026-02692-w (2026).","DOI":"10.1007\/s40670-026-02692-w"},{"key":"7261_CR26","unstructured":"Kweon, S. et al. KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations. arXiv preprint arXiv:240301469 (2024)."},{"key":"7261_CR27","doi-asserted-by":"crossref","unstructured":"Liu, J. et al. KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations. International Workshop on Agentic AI for Medicine. 2025:300-9.","DOI":"10.1007\/978-3-032-06004-4_30"},{"key":"7261_CR28","first-page":"62991","volume":"36","author":"Y Huang","year":"2023","unstructured":"Huang, Y. et al. C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models. Advances in Neural Information Processing Systems 36, 62991\u20133010 (2023).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"7261_CR29","unstructured":"Liu, J. et al. Benchmarking large language models on CMExam - a comprehensive chinese medical exam dataset. Proceedings of the 37th International Conference on Neural Information Processing Systems; New Orleans, LA, USA: Curran Associates Inc.; p. Article 2283 (2023)."},{"key":"7261_CR30","doi-asserted-by":"publisher","unstructured":"Zong H, Shen B. A Dataset for Evaluating Large Language Models on Chinese National Medical Licensing Examinations, https:\/\/doi.org\/10.5281\/zenodo.18951465 (2026).","DOI":"10.5281\/zenodo.18951465"},{"key":"7261_CR31","unstructured":"Comanici, G. et al. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:250706261 (2025)."},{"issue":"8081","key":"7261_CR32","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D. et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081), 633\u20138, https:\/\/doi.org\/10.1038\/s41586-025-09422-z (2025).","journal-title":"Nature"},{"key":"7261_CR33","unstructured":"Team Q. Qwen2 technical report. arXiv preprint arXiv:240710671. 2024;2(8)."},{"key":"7261_CR34","unstructured":"Achiam, J. et al. GPT-4 technical report. arXiv preprint arXiv:230308774 (2023)."},{"key":"7261_CR35","unstructured":"Dubey, A. et al. The Llama 3 herd of models. arXiv e-prints. 2024:arXiv: 2407.21783."},{"issue":"9","key":"7261_CR36","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1093\/jamia\/ocad259","volume":"31","author":"Y Hu","year":"2024","unstructured":"Hu, Y. et al. Improving large language models for clinical named entity recognition via prompt engineering. J Am Med Inform Assoc. 31(9), 1812\u201320, https:\/\/doi.org\/10.1093\/jamia\/ocad259 (2024).","journal-title":"J Am Med Inform Assoc."},{"key":"7261_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.109033","volume":"271","author":"R Wu","year":"2025","unstructured":"Wu, R. et al. Improving large language models for miRNA information extraction via prompt engineering. Comput Methods Programs Biomed 271, 109033, https:\/\/doi.org\/10.1016\/j.cmpb.2025.109033 (2025).","journal-title":"Comput Methods Programs Biomed"}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07261-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07261-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07261-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T23:31:23Z","timestamp":1781652683000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07261-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["7261"],"URL":"https:\/\/doi.org\/10.1038\/s41597-026-07261-9","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"4 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"898"}}