{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T22:55:52Z","timestamp":1790636152341,"version":"4.1.0"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003790","name":"Hiroshima University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003790","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001700","name":"Government of Japan Ministry of Education Culture Sports Science and Technology","doi-asserted-by":"publisher","award":["25K15961"],"award-info":[{"award-number":["25K15961"]}],"id":[{"id":"10.13039\/501100001700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Dentistry"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jdent.2026.106675","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T01:02:45Z","timestamp":1775437365000},"page":"106675","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Beyond exam accuracy: Tracking a persistent-failure set reveals visual dental reasoning gaps in multimodal LLMs"],"prefix":"10.1016","volume":"170","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7057-1955","authenticated-orcid":false,"given":"Yuichi","family":"Mine","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsuyoshi","family":"Taji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5901-0012","authenticated-orcid":false,"given":"Shota","family":"Okazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saori","family":"Takeda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saiji","family":"Shimoe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Kaku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroki","family":"Nikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1274-8991","authenticated-orcid":false,"given":"Naoya","family":"Kakimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeshi","family":"Murayama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jdent.2026.106675_bib0001","doi-asserted-by":"crossref","unstructured":"Z. Li, X. Wu, H. Du, F. Liu, H. Nghiem, G. Shi, A survey of state of the art large vision language models: alignment, benchmark, evaluations and challenges, arXiv preprint (2025), arXiv:2501.02189, 1.","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"10.1016\/j.jdent.2026.106675_bib0002","unstructured":"Introducing GPT-5.2. https:\/\/openai.com\/index\/introducing-gpt-5-2\/ [Accessed January 31, 2026]."},{"key":"10.1016\/j.jdent.2026.106675_bib0003","unstructured":"Introducing Claude Opus 4.5. https:\/\/www.anthropic.com\/news\/claude-opus-4-5 [Accessed January 31, 2026]."},{"key":"10.1016\/j.jdent.2026.106675_bib0004","unstructured":"Gemini 3 Pro: the frontier of vision AI. https:\/\/blog.google\/innovation-and-ai\/technology\/developers-tools\/gemini-3-pro-vision\/ [Accessed January 31, 2026]."},{"key":"10.1016\/j.jdent.2026.106675_bib0005","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s44267-025-00099-6","article-title":"Efficient multimodal large language models: a survey","volume":"3","author":"Jin","year":"2025","journal-title":"Vis. Intell."},{"key":"10.1016\/j.jdent.2026.106675_bib0006","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41405-024-00277-6","article-title":"Innovation and application of large language models (LLMs) in dentistry - a scoping review","volume":"10","author":"Umer","year":"2024","journal-title":"BDJ Open"},{"key":"10.1016\/j.jdent.2026.106675_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.identj.2025.103854","article-title":"A scoping review of large language models in dental education: applications, challenges, and prospects","volume":"75","author":"Kong","year":"2025","journal-title":"Int. Dent. J."},{"key":"10.1016\/j.jdent.2026.106675_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.jdent.2025.106187","article-title":"The ethics and governance of large language models in dentistry: a framework for research and clinical implementation","volume":"164","author":"Rokhshad","year":"2026","journal-title":"J. Dent."},{"key":"10.1016\/j.jdent.2026.106675_bib0009","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.identj.2024.10.014","article-title":"Large language models in dental licensing examinations: systematic review and meta-analysis","volume":"75","author":"Liu","year":"2025","journal-title":"Int. Dent. J."},{"key":"10.1016\/j.jdent.2026.106675_bib0010","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1016\/j.jds.2025.07.010","article-title":"Impact of language and question types on ChatGPT-4o's performance in answering oral pathology questions from Taiwan national dental licensing examinations","volume":"20","author":"Wu","year":"2025","journal-title":"J. Dent. Sci."},{"key":"10.1016\/j.jdent.2026.106675_bib0011","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1186\/s12903-025-07540-8","article-title":"From accuracy to robustness: a comparative study of five advanced large language models on the Chinese dental licensing examination","volume":"25","author":"Zhang","year":"2025","journal-title":"BMC Oral Health"},{"key":"10.1016\/j.jdent.2026.106675_bib0012","doi-asserted-by":"crossref","first-page":"1734","DOI":"10.1186\/s12909-025-08315-z","article-title":"Performance comparison of large language models on pediatric dentistry questions in the Turkish dentistry specialization examination","volume":"25","author":"Ba\u015fkan","year":"2025","journal-title":"BMC Med. Educ."},{"key":"10.1016\/j.jdent.2026.106675_bib0013","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.jds.2025.07.020","article-title":"Evaluation of GPT-4o and Gemini Advanced on the Korean national dental licensing examination: accuracy, consistency, and question generation","volume":"21","author":"Song","year":"2026","journal-title":"J. Dent. Sci."},{"key":"10.1016\/j.jdent.2026.106675_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.jdent.2023.104796","article-title":"Natural language processing: chances and challenges in dentistry","volume":"141","author":"B\u00fcttner","year":"2024","journal-title":"J. Dent."},{"key":"10.1016\/j.jdent.2026.106675_bib0015","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1016\/j.jds.2025.03.018","article-title":"Benchmarking multimodal language models on the dental licensing examination: challenges with clinical image interpretation","volume":"20","author":"Mine","year":"2025","journal-title":"J. Dent. Sci."},{"key":"10.1016\/j.jdent.2026.106675_bib0016","unstructured":"C. Xu, S. Guan, D. Greene, M.T. Kechadi, Benchmark data contamination of large language models: a survey, arXiv preprint (2024), arXiv:2406.04244."},{"key":"10.1016\/j.jdent.2026.106675_bib0017","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"10080","article-title":"Benchmarking large language models under data contamination: a survey from static to dynamic evaluation","author":"Chen","year":"2025"},{"key":"10.1016\/j.jdent.2026.106675_bib0018","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.jdent.2026.106675_bib0019","unstructured":"The Ministry of Health, Labour and Welfare of Japan, Questions and correct answers for the 118th national dental examination. Available at: https:\/\/www.mhlw.go.jp\/seisakunitsuite\/bunya\/kenkou_iryou\/iryou\/topics\/tp250428-02.html [Accessed January 31, 2026]."},{"key":"10.1016\/j.jdent.2026.106675_bib0020","series-title":"The Reference Manual of Pediatric Dentistry","first-page":"497","article-title":"Management of the developing dentition and occlusion in pediatric dentistry","year":"2025"},{"key":"10.1016\/j.jdent.2026.106675_bib0021","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1038\/s41368-025-00351-1","article-title":"Expert consensus on imaging diagnosis and analysis of early correction of childhood malocclusion","volume":"17","author":"Lin","year":"2025","journal-title":"Int. J. Oral Sci."},{"key":"10.1016\/j.jdent.2026.106675_bib0022","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1111\/ipd.70029","article-title":"Challenges and limitations of multimodal large language models in interpreting pediatric panoramic radiographs","volume":"36","author":"Mine","year":"2026","journal-title":"Int. J. Paediatr. Dent."},{"key":"10.1016\/j.jdent.2026.106675_bib0023","article-title":"Leveraging multimodal large language model chatbots in oral radiology: a comprehensive evaluation using questions from a Korean dental university","author":"Jeong","year":"2025","journal-title":"Dentomaxillofac. Radiol."},{"key":"10.1016\/j.jdent.2026.106675_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.jds.2025.08.037","article-title":"Performance of large language models on image-based oral pathology questions from the Japanese national dental examination","author":"Watanabe","year":"2025","journal-title":"J. Dent. Sci."},{"key":"10.1016\/j.jdent.2026.106675_bib0025","doi-asserted-by":"crossref","DOI":"10.2196\/84120","article-title":"Knowledge-practice performance gap in clinical large language models: systematic review of 39 benchmarks","volume":"27","author":"Gong","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.jdent.2026.106675_bib0026","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: a systematic review","volume":"333","author":"Bedi","year":"2025","journal-title":"JAMA"},{"key":"10.1016\/j.jdent.2026.106675_bib0027","unstructured":"R.K. Arora, J. Wei, R.S. Hicks, et al. Healthbench: evaluating large language models towards improved human health, arXiv preprint (2025), arXiv:2505.08775."},{"key":"10.1016\/j.jdent.2026.106675_bib0028","article-title":"HealthBench: advancing AI evaluation in healthcare, but not yet clinically ready","volume":"11","author":"Liu","year":"2025","journal-title":"Digit. Health"},{"key":"10.1016\/j.jdent.2026.106675_bib0029","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-02277-8","article-title":"A novel evaluation benchmark for medical LLMs illuminating safety and effectiveness in clinical domains","author":"Wang","year":"2025","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.jdent.2026.106675_bib0030","doi-asserted-by":"crossref","DOI":"10.1056\/AIdbp2500144","article-title":"MedAgentBench: a virtual EHR environment to benchmark medical LLM agents","volume":"2","author":"Jiang","year":"2025","journal-title":"NEJM AI"},{"key":"10.1016\/j.jdent.2026.106675_bib0031","article-title":"Comparative analysis of diagnostic prediction and clinical reasoning of large language models in complex endodontic case scenarios","author":"Sahoo","year":"2025","journal-title":"J. Dent."}],"container-title":["Journal of Dentistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0300571226003465?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0300571226003465?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:03:26Z","timestamp":1783422206000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0300571226003465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":31,"alternative-id":["S0300571226003465"],"URL":"https:\/\/doi.org\/10.1016\/j.jdent.2026.106675","relation":{},"ISSN":["0300-5712"],"issn-type":[{"value":"0300-5712","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond exam accuracy: Tracking a persistent-failure set reveals visual dental reasoning gaps in multimodal LLMs","name":"articletitle","label":"Article Title"},{"value":"Journal of Dentistry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jdent.2026.106675","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"106675"}}