{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T10:46:54Z","timestamp":1793357214677,"version":"4.5.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Anhui Province Scientific Research Preparation Program Project","award":["2022AH050734"],"award-info":[{"award-number":["2022AH050734"]}]},{"name":"\u201cFeng Yuan\u201dProgram","award":["2022xkfyhz03"],"award-info":[{"award-number":["2022xkfyhz03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Oral Health"],"DOI":"10.1186\/s12903-025-07540-8","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T07:32:33Z","timestamp":1766388753000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["From accuracy to robustness: a comparative study of five advanced large language models on the Chinese dental licensing examination"],"prefix":"10.1186","volume":"25","author":[{"given":"Jiarui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Ubuzima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaoyang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"En-Hsuan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huifang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2109-8632","authenticated-orcid":false,"given":"Lei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4375-6820","authenticated-orcid":false,"given":"Tingting","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"7540_CR1","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.aopr.2025.05.001","volume":"5","author":"P Xu","year":"2025","unstructured":"Xu P, Wu Y, Jin K, Chen X, He M, Shi D. DeepSeek-R1 outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in bilingual complex ophthalmology reasoning. Adv Ophthalmol Pract Res. 2025;5:189\u201395.","journal-title":"Adv Ophthalmol Pract Res"},{"key":"7540_CR2","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1186\/s12911-025-02954-4","volume":"25","author":"S Shool","year":"2025","unstructured":"Shool S, Adimi S, Saboori Amleshi R, Bitaraf E, Golpira R, Tara M. A systematic review of large language model (LLM) evaluations in clinical medicine. BMC Med Inform Decis Mak. 2025;25:117.","journal-title":"BMC Med Inform Decis Mak"},{"key":"7540_CR3","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat Med. 2023;29:1930\u201340.","journal-title":"Nat Med"},{"key":"7540_CR4","doi-asserted-by":"publisher","DOI":"10.2196\/51926","volume":"26","author":"X Liu","year":"2024","unstructured":"Liu X, Wu J, Shao A, Shen W, Ye P, Wang Y, et al. Uncovering language disparity of ChatGPT on retinal vascular disease classification: cross-sectional study. J Med Internet Res. 2024;26:e51926.","journal-title":"J Med Internet Res"},{"key":"7540_CR5","first-page":"401","volume":"27","author":"Z Hu","year":"2024","unstructured":"Hu Z, Xu Z, Shi P, Zhang D, Yue Q, Zhang J, et al. Performance of large language models in the national dental licensing examination in China: a comparative analysis of ChatGPT, GPT-4, and New Bing. Int J Comput Dent. 2024;27:401\u201311.","journal-title":"Int J Comput Dent"},{"key":"7540_CR6","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1111\/eje.13073","volume":"29","author":"YT Xiong","year":"2025","unstructured":"Xiong YT, Zhan ZZ, Zhong CL, Zeng W, Guo JX, Tang W, et al. Evaluating the performance of large language models (LLMs) in answering and analysing the Chinese dental licensing examination. Eur J Dent Educ. 2025;29:332\u201340.","journal-title":"Eur J Dent Educ"},{"key":"7540_CR7","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s00276-025-03723-8","volume":"47","author":"BN Gokkurt Yilmaz","year":"2025","unstructured":"Gokkurt Yilmaz BN, Ozbey F, Yilmaz BE. Evaluation of the performance of different large language models on head and neck anatomy questions in the dentistry specialization exam in Turkey. Surg Radiol Anat. 2025;47:211.","journal-title":"Surg Radiol Anat"},{"key":"7540_CR8","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1186\/s12903-025-05926-2","volume":"25","author":"BE Yilmaz","year":"2025","unstructured":"Yilmaz BE, Gokkurt Yilmaz BN, Ozbey F. Artificial intelligence performance in answering multiple-choice oral pathology questions: a comparative analysis. BMC Oral Health. 2025;25:573.","journal-title":"BMC Oral Health"},{"key":"7540_CR9","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1186\/s12909-025-07195-7","volume":"25","author":"S Ramlogan","year":"2025","unstructured":"Ramlogan S, Raman V, Ramlogan S. A pilot study of the performance of Chat GPT and other large language models on a written final year periodontology exam. BMC Med Educ. 2025;25:727.","journal-title":"BMC Med Educ"},{"key":"7540_CR10","unstructured":"Nori H, King N, McKinney SM, Carignan D, Horvitz E. Capabilities of GPT-4 on medical challenge problems. 2023. Preprint at https:\/\/ui.adsabs.harvard.edu\/abs\/2023arXiv230313375N."},{"key":"7540_CR11","unstructured":"Osazuwa Ness R, Matton K, Helm H, Zhang S, Bajwa J, Priebe CE, et al. MedFuzz: exploring the robustness of large language models in medical question answering. 2024. Preprint at https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240606573O."},{"key":"7540_CR12","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.identj.2024.10.014","volume":"75","author":"M Liu","year":"2025","unstructured":"Liu M, Okuhara T, Huang W, Ogihara A, Nagao HS, Okada H, et al. Large language models in dental licensing examinations: systematic review and meta-analysis. Int Dent J. 2025;75:213\u201322.","journal-title":"Int Dent J"},{"key":"7540_CR13","unstructured":"OpenAI. Hello GPT-4o. 2025. https:\/\/openai.com\/zh-Hans-CN\/index\/hello-gpt-4o\/. Accessed 15 Aug 2025."},{"key":"7540_CR14","unstructured":"OpenAI. GPT-4o System Card. 2025. https:\/\/openai.com\/zh-Hant-HK\/index\/gpt-4o-system-card\/. Accessed 20 Aug 2025."},{"key":"7540_CR15","unstructured":"OpenAI Introducing OpenAI o3 and o4-mini. 2025. https:\/\/openai.com\/zh-Hans-CN\/index\/introducing-o3-and-o4-mini\/. Accessed 15 Aug 2025."},{"key":"7540_CR16","unstructured":"OpenAI. OpenAI o3 and o4-mini System Card. 2025. https:\/\/openai.com\/ja-JP\/index\/o3-o4-mini-system-card\/. Accessed 15 Aug 2025."},{"key":"7540_CR17","unstructured":"OpenAI. Introducing GPT-5. 2025. https:\/\/openai.com\/zh-Hans-CN\/index\/introducing-gpt-5\/. Accessed 14 Aug 2025."},{"key":"7540_CR18","unstructured":"OpenAI. GPT-5 System Card. 2025. https:\/\/cdn.openai.com\/gpt-5-system-card.pdf. Accessed 15 Aug 2025."},{"key":"7540_CR19","unstructured":"Google DeepMind. Gemini 2.5 Pro Model Card. 2025. https:\/\/storage.googleapis.com\/model-cards\/documents\/gemini-2.5-pro.pdf. Accessed 15 Aug 2025."},{"key":"7540_CR20","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s10916-025-02213-z","volume":"49","author":"J Wu","year":"2025","unstructured":"Wu J, Wang Z, Qin Y. Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese national medical licensing examination: a comparative study. J Med Syst. 2025;49:74.","journal-title":"J Med Syst"},{"key":"7540_CR21","unstructured":"deepseek-ai. DeepSeek-R1. 2025. https:\/\/github.com\/deepseek-ai\/DeepSeek-R1. Accessed 15 Aug 2025."},{"key":"7540_CR22","doi-asserted-by":"publisher","DOI":"10.2196\/52784","volume":"10","author":"S Ming","year":"2024","unstructured":"Ming S, Guo Q, Cheng W, Lei B. Influence of model evolution and system roles on ChatGPT\u2019s performance in Chinese medical licensing exams: comparative study. JMIR Med Educ. 2024;10:e52784.","journal-title":"JMIR Med Educ"},{"key":"7540_CR23","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1237432","volume":"10","author":"W Tong","year":"2023","unstructured":"Tong W, Guan Y, Chen J, Huang X, Zhong Y, Zhang C, et al. Artificial intelligence in global health equity: an evaluation and discussion on the application of ChatGPT, in the Chinese national medical licensing examination. Front Med. 2023;10:1237432.","journal-title":"Front Med"},{"key":"7540_CR24","unstructured":"Vishwanath K, Alyakin A, Alber DA, Lee JV, Kondziolka D, Oermann EK. Medical large language models are easily distracted. 2025. Preprint at https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250401201V."},{"key":"7540_CR25","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager P, Jungmann F, Holland R, Bhagat K, Hubrecht I, Knauer M, et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat Med. 2024;30:2613\u201322.","journal-title":"Nat Med"},{"key":"7540_CR26","unstructured":"Anthropic. System Card: Claude Opus 4 & Claude Sonnet 4. 2025. https:\/\/www-cdn.anthropic.com\/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf. Accessed 16 Aug 2025."},{"key":"7540_CR27","unstructured":"Anthropic. Introducing Claude 4. 2025. https:\/\/www.anthropic.com\/news\/claude-4. Accessed 16 Aug 2025."},{"key":"7540_CR28","unstructured":"Chen S, Li X, Zhang M, Hanchen Jiang E, Zeng Q, Yu C-H. CARES: comprehensive evaluation of safety and adversarial robustness in medical LLMs. 2025. Preprint at https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250511413C."},{"key":"7540_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.101118","volume":"6","author":"L Qin","year":"2025","unstructured":"Qin L, Chen Q, Zhou Y, Chen Z, Li Y, Liao L, et al. A survey of multilingual large language models. Patterns. 2025;6:101118.","journal-title":"Patterns"},{"key":"7540_CR30","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1162\/coli_a_00557","volume":"51","author":"DA Haslett","year":"2025","unstructured":"Haslett DA. Tokenization changes meaning in large language models: evidence from Chinese. Comput Linguist. 2025;51:785\u2013814.","journal-title":"Comput Linguist"},{"key":"7540_CR31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0317423","volume":"20","author":"HC Nguyen","year":"2025","unstructured":"Nguyen HC, Dang HP, Nguyen TL, Hoang V, Nguyen VA. Accuracy of latest large language models in answering multiple choice questions in dentistry: a comparative study. PLoS One. 2025;20:e0317423.","journal-title":"PLoS One"},{"key":"7540_CR32","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98949-2","volume":"15","author":"D Luo","year":"2025","unstructured":"Luo D, Liu M, Yu R, Liu Y, Jiang W, Fan Q, et al. Evaluating the performance of GPT-3.5, GPT-4, and GPT-4o in the Chinese national medical licensing examination. Sci Rep. 2025;15:14119.","journal-title":"Sci Rep"},{"key":"7540_CR33","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M, et al. Toward expert-level medical question answering with large language models. Nat Med. 2025;31:943\u201350.","journal-title":"Nat Med"},{"key":"7540_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.identj.2025.100847","volume":"75","author":"H Fukuda","year":"2025","unstructured":"Fukuda H, Morishita M, Muraoka K, Yamaguchi S, Nakamura T, Habu M, et al. Evaluating the accuracy and performance of ChatGPT-4o in solving Japanese national dental technician examination. Int Dent J. 2025;75:100847.","journal-title":"Int Dent J"},{"key":"7540_CR35","first-page":"248","volume":"51","author":"YW Chen","year":"2020","unstructured":"Chen YW, Stanley K, Att W. Artificial intelligence in dentistry: current applications and future perspectives. Quintessence Int. 2020;51:248\u201357.","journal-title":"Quintessence Int"},{"key":"7540_CR36","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et al. Language models are few-shot learners. 2020. Preprint at https:\/\/ui.adsabs.harvard.edu\/abs\/2020arXiv200514165B."},{"key":"7540_CR37","doi-asserted-by":"publisher","DOI":"10.2196\/52483","volume":"10","author":"Y Wu","year":"2024","unstructured":"Wu Y, Zheng Y, Feng B, Yang Y, Kang K, Zhao A. Embracing ChatGPT for medical education: exploring its impact on doctors and medical students. JMIR Med Educ. 2024;10:e52483.","journal-title":"JMIR Med Educ"},{"key":"7540_CR38","doi-asserted-by":"publisher","DOI":"10.2196\/57896","volume":"26","author":"T Xu","year":"2024","unstructured":"Xu T, Weng H, Liu F, Yang L, Luo Y, Ding Z, et al. Current status of ChatGPT use in medical education: potentials, challenges, and strategies. J Med Internet Res. 2024;26:e57896.","journal-title":"J Med Internet Res"},{"key":"7540_CR39","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s41368-023-00239-y","volume":"15","author":"H Huang","year":"2023","unstructured":"Huang H, Zheng O, Wang D, Yin J, Wang Z, Ding S, et al. ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model. Int J Oral Sci. 2023;15:29.","journal-title":"Int J Oral Sci"},{"key":"7540_CR40","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1111\/jerd.13046","volume":"35","author":"F Eggmann","year":"2023","unstructured":"Eggmann F, Weiger R, Zitzmann NU, Blatz MB. Implications of large language models such as ChatGPT for dental medicine. J Esthet Restor Dent. 2023;35:1098\u2013102.","journal-title":"J Esthet Restor Dent"},{"key":"7540_CR41","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1038\/s41591-024-03258-2","volume":"30","author":"SR Pfohl","year":"2024","unstructured":"Pfohl SR, Cole-Lewis H, Sayres R, Neal D, Asiedu M, Dieng A, et al. A toolbox for surfacing health equity harms and biases in large language models. Nat Med. 2024;30:3590\u2013600.","journal-title":"Nat Med"},{"key":"7540_CR42","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1186\/s12903-025-06624-9","volume":"25","author":"A Arpaci","year":"2025","unstructured":"Arpaci A, Ozturk AU, Okur I, Sadry S. Evaluation of the accuracy of ChatGPT-4 and Gemini\u2019s responses to the World Dental Federation\u2019s frequently asked questions on oral health. BMC Oral Health. 2025;25:1293.","journal-title":"BMC Oral Health"},{"key":"7540_CR43","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41404-023-1944-7","volume":"36","author":"M Pahadia","year":"2023","unstructured":"Pahadia M. ChatGPT in dentistry: is it worth the hype? BDJ In Pract. 2023;36:5\u20135.","journal-title":"BDJ In Pract"}],"container-title":["BMC Oral Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12903-025-07540-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-07540-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-07540-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T20:38:24Z","timestamp":1767040704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12903-025-07540-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["7540"],"URL":"https:\/\/doi.org\/10.1186\/s12903-025-07540-8","relation":{},"ISSN":["1472-6831"],"issn-type":[{"value":"1472-6831","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]},"assertion":[{"value":"11 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1975"}}