{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T04:29:31Z","timestamp":1793852971015,"version":"4.6.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":61,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-51934-9","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:06:20Z","timestamp":1778249180000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking large language models on persian surgical subspecialty board examinations: a comparative study of ChatGPT-4o, ChatGPT-5, and Gemini 2.5 Flash"],"prefix":"10.1038","volume":"16","author":[{"given":"Shahab","family":"Sheikhalishahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farzad","family":"Rafiei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyed Masoud","family":"Hosseini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Haddadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saina","family":"Sadeghipour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"issue":"1","key":"51934_CR1","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s40670-024-02206-6","volume":"35","author":"A Aster","year":"2025","unstructured":"Aster, A. et al. ChatGPT and other large language models in medical education: Scoping literature review. Med. Sci. Educ. 35(1), 555\u2013567 (2025).","journal-title":"Med. Sci. Educ."},{"issue":"1","key":"51934_CR2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1038\/s43856-024-00717-2","volume":"5","author":"F Busch","year":"2025","unstructured":"Busch, F. et al. Current applications and challenges in large language models for patient care: A systematic review. Commun. Med. 5(1), 26 (2025).","journal-title":"Commun. Med."},{"key":"51934_CR3","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13060603","author":"J Vrdoljak","year":"2025","unstructured":"Vrdoljak, J., Boban, Z., Vilovi\u0107, M., Kumri\u0107, M. & Bo\u017ei\u0107, J. A review of large language models in medical education, clinical decision support, and healthcare administration. Healthcare https:\/\/doi.org\/10.3390\/healthcare13060603 (2025).","journal-title":"Healthcare"},{"issue":"1","key":"51934_CR4","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s11657-025-01587-4","volume":"20","author":"CR Lin","year":"2025","unstructured":"Lin, C. R. et al. Multiple large language models versus clinical guidelines for postmenopausal osteoporosis: a comparative study of ChatGPT-3.5, ChatGPT-4.0, ChatGPT-4o, Google Gemini, Google Gemini Advanced, and Microsoft Copilot. Arch. Osteoporos. 20(1), 120 (2025).","journal-title":"Arch. Osteoporos."},{"issue":"5","key":"51934_CR5","doi-asserted-by":"publisher","first-page":"334","DOI":"10.64912\/RADT.2025.JDYI8440","volume":"96","author":"KR Clark","year":"2025","unstructured":"Clark, K. R. Comparative analysis of LLMs\u2019 performance on a practice radiography certification exam. Radiol. Technol. 96(5), 334\u2013342 (2025).","journal-title":"Radiol. Technol."},{"issue":"5","key":"51934_CR6","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1053\/j.jvca.2024.01.032","volume":"38","author":"AA Khan","year":"2024","unstructured":"Khan, A. A. et al. Artificial intelligence for anesthesiology board-style examination questions: Role of large language models. J. Cardiothorac. Vasc. Anesth. 38(5), 1251\u20131259 (2024).","journal-title":"J. Cardiothorac. Vasc. Anesth."},{"issue":"7","key":"51934_CR7","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1093\/ced\/llad197","volume":"49","author":"L Passby","year":"2024","unstructured":"Passby, L., Jenko, N. & Wernham, A. Performance of ChatGPT on specialty certificate examination in dermatology multiple-choice questions. Clin. Exp. Dermatol. 49(7), 722\u2013727 (2024).","journal-title":"Clin. Exp. Dermatol."},{"issue":"5","key":"51934_CR8","doi-asserted-by":"publisher","first-page":"269","DOI":"10.4174\/astr.2023.104.5.269","volume":"104","author":"N Oh","year":"2023","unstructured":"Oh, N., Choi, G. S. & Lee, W. Y. ChatGPT goes to the operating room: Evaluating GPT-4 performance and its potential in surgical education and training in the era of large language models. Ann. Surg. Treat. Res. 104(5), 269\u2013273 (2023).","journal-title":"Ann. Surg. Treat. Res."},{"issue":"1","key":"51934_CR9","doi-asserted-by":"publisher","first-page":"22129","DOI":"10.1038\/s41598-023-49483-6","volume":"13","author":"A Madrid-Garc\u00eda","year":"2023","unstructured":"Madrid-Garc\u00eda, A. et al. Harnessing ChatGPT and GPT-4 for evaluating the rheumatology questions of the Spanish access exam to specialized medical training. Sci Rep. 13(1), 22129 (2023).","journal-title":"Sci Rep."},{"issue":"1","key":"51934_CR10","doi-asserted-by":"publisher","first-page":"7274","DOI":"10.1038\/s41598-026-38716-z","volume":"16","author":"F Rafiei","year":"2026","unstructured":"Rafiei, F. et al. Evaluation of large Language model performance on Persian rheumatology board exams: Accuracy and clinical reasoning of GPT-4o vs. GPT-5.1. Sci Rep 16(1), 7274 (2026).","journal-title":"Sci Rep"},{"issue":"1","key":"51934_CR11","doi-asserted-by":"publisher","DOI":"10.1080\/10872981.2025.2554678","volume":"30","author":"M Elzayyat","year":"2025","unstructured":"Elzayyat, M., Mohammad, J. N. & Zaqout, S. Assessing LLM-generated vs. expert-created clinical anatomy MCQs: A student perception-based comparative study in medical education. Med. Educ. Online 30(1), 2554678 (2025).","journal-title":"Med. Educ. Online"},{"issue":"1","key":"51934_CR12","doi-asserted-by":"publisher","first-page":"37545","DOI":"10.1038\/s41598-025-22437-w","volume":"15","author":"O Bolgova","year":"2025","unstructured":"Bolgova, O. & Mavrych, V. Evolution of AI in anatomy education study based on comparison of current large language models against historical ChatGPT performance. Sci. Rep. 15(1), 37545 (2025).","journal-title":"Sci. Rep."},{"key":"51934_CR13","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.plrev.2024.10.013","volume":"51","author":"Y Lu","year":"2024","unstructured":"Lu, Y., Aleta, A., Du, C., Shi, L. & Moreno, Y. LLMs and generative agent-based models for complex systems research. Phys. Life Rev. 51, 283\u2013293 (2024).","journal-title":"Phys. Life Rev."},{"issue":"1","key":"51934_CR14","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-024-01029-4","volume":"7","author":"L Wang","year":"2024","unstructured":"Wang, L. et al. Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. npj Digit. Med. 7(1), 41 (2024).","journal-title":"npj Digit. Med."},{"key":"51934_CR15","first-page":"101048","volume":"45","author":"J Qiu","year":"2024","unstructured":"Qiu, J., Yuan, W. & Lam, K. The application of multimodal large language models in medicine. Lancet Reg. Health. 45, 101048 (2024).","journal-title":"Lancet Reg. Health."},{"key":"51934_CR16","doi-asserted-by":"publisher","first-page":"e59505","DOI":"10.2196\/59505","volume":"26","author":"R AlSaad","year":"2024","unstructured":"AlSaad, R. et al. Multimodal large language models in health care: Applications, challenges, and future outlook. J. Med. Internet Res. 26, e59505 (2024).","journal-title":"J. Med. Internet Res."},{"issue":"1","key":"51934_CR17","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1186\/s12909-024-06309-x","volume":"24","author":"Y Chen","year":"2024","unstructured":"Chen, Y. et al. Performance of ChatGPT and Bard on the medical licensing examinations varies across different cultures: A comparison study. BMC Med. Educ. 24(1), 1372 (2024).","journal-title":"BMC Med. Educ."},{"issue":"11","key":"51934_CR18","doi-asserted-by":"publisher","first-page":"2792","DOI":"10.7150\/ijms.111780","volume":"22","author":"E Yu","year":"2025","unstructured":"Yu, E. et al. Large language models in medicine: Applications, challenges, and future directions. Int. J. Med. Sci. 22(11), 2792\u20132801 (2025).","journal-title":"Int. J. Med. Sci."},{"key":"51934_CR19","doi-asserted-by":"publisher","first-page":"1504532","DOI":"10.3389\/fmed.2024.1504532","volume":"11","author":"S Maaz","year":"2024","unstructured":"Maaz, S., Palaganas, J. C., Palaganas, G. & Bajwa, M. A guide to prompt design: Foundations and applications for healthcare simulationists. Front. Med. (Lausanne) 11, 1504532 (2024).","journal-title":"Front. Med. (Lausanne)"},{"issue":"5","key":"51934_CR20","doi-asserted-by":"publisher","first-page":"109713","DOI":"10.1016\/j.isci.2024.109713","volume":"27","author":"X Meng","year":"2024","unstructured":"Meng, X. et al. The application of large language models in medicine: A scoping review. iScience 27(5), 109713 (2024).","journal-title":"iScience"},{"key":"51934_CR21","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 (2024).","journal-title":"J. Med. Internet Res."},{"issue":"1","key":"51934_CR22","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s40561-024-00316-7","volume":"11","author":"C Zhai","year":"2024","unstructured":"Zhai, C., Wibowo, S. & Li, L. D. The effects of over-reliance on AI dialogue systems on students\u2019 cognitive abilities: A systematic review. Smart Learn. Environ. 11(1), 28 (2024).","journal-title":"Smart Learn. Environ."},{"key":"51934_CR23","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Schwartz, R., Vassilev, A., Greene, K., Perine, L. & Burt, A., et al. Towards a standard for identifying and managing bias in artificial intelligence: US Department of Commerce, National Institute of Standards and Technology\u2026 (2022).","DOI":"10.6028\/NIST.SP.1270"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51934-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51934-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51934-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:22:52Z","timestamp":1783470172000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51934-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["51934"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-51934-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-8080315\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]},"assertion":[{"value":"10 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21139"}}