Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients

Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients Omran Altos, Gang Chen, Ahmed Bashah, Ahmed Awad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7620716/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Jan, 2026 Read the published version in Journal of Translational Medicine → Version 1 posted 4 You are reading this latest preprint version Abstract Background Artificial intelligence (AI) has shown remarkable potential in medical education and clinical decision support, yet its role in dentistry—particularly in the management of medically compromised patients—remains largely unexplored. No previous study has systematically benchmarked the performance of advanced large language models (LLMs) in this high-risk domain. Objective This study provides the first comparative evaluation of three LLMs—GPT-5, DeepSeek, and Claude—on multiple-choice questions (MCQs) specifically designed for dental management of medically compromised patients. Methods A total of 72 validated MCQs were constructed from the 10th edition of Little & Falace’s Dental Management of the Medically Compromised Patient, covering 18 systemic conditions relevant to dental practice. Each model was independently assessed under identical conditions. Accuracy, agreement with the gold standard answers from the textbook, and error patterns were analyzed. Results GPT-5 achieved the highest accuracy (90.28%), followed by Claude (88.89%) and DeepSeek (87.50%) . Performance varied across systemic conditions, with all models demonstrating lower accuracy in complex scenarios such as infective endocarditis and bleeding disorders. Qualitative analysis revealed differences in reasoning depth, error types, and consistency of responses. Conclusions This is the first study to benchmark multiple frontier LLMs in dentistry, focusing on medically compromised patients—a group where safe and accurate decision-making is essential. The findings highlight both the promise and limitations of AI in dental education and clinical guidance. By systematically identifying strengths and weaknesses, this work provides an evidence base for integrating LLMs into dental curricula and decision-support systems, while underscoring the need for human oversight in complex medical cases. Clinical significance Generative AI models, including GPT-5, DeepSeek, and Claude, demonstrated high accuracy in case-based dental decision-making for medically compromised patients. Their integration could enhance dental education and clinical support. However, variability in performance underscores the need for cautious use and further validation before applying AI tools in complex patient care. Artificial intelligence dental education medically compromised patients case-based learning ChatGPT Claude DeepSeek Full Text Cite Share Download PDF Status: Published Journal Publication published 29 Jan, 2026 Read the published version in Journal of Translational Medicine → Version 1 posted Reviewers agreed at journal 02 Oct, 2025 Reviewers invited by journal 29 Sep, 2025 Editor assigned by journal 16 Sep, 2025 First submitted to journal 15 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7620716","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":522412814,"identity":"5a661287-00a9-4f70-910d-97c0b2d6f6b8","order_by":0,"name":"Omran Altos","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYFAD9gYgYWBBrPIEIOY5ANIiQYoWCRDBQIQWfrGzDz8X/rBJnD/z+dUNPwokGPjbuxPwapGcnW4sPSMhLXHD7Zyymz1Ah0mcObsBrxaD22kM0jwJhxM3SOek3eABajGQyCWohfk3SMv8mWfSbv4hUgsb2JaGG+zHbhNli+TsNDZrnrQ04w1ncthuyxhI8BD0C790GvNtHhsb2fntx5/dfPPHRo6/vRe/FiTAYwAmiVUOAuwPSFE9CkbBKBgFIwgAADiiRHd3mFomAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0008-4100-4266","institution":"Dalian Medical University","correspondingAuthor":true,"prefix":"","firstName":"Omran","middleName":"","lastName":"Altos","suffix":""},{"id":522412815,"identity":"17093fe8-56e2-40c0-a85a-5e19321ea98b","order_by":1,"name":"Gang Chen","email":"","orcid":"","institution":"First Affiliated Hospital of Dalian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Gang","middleName":"","lastName":"Chen","suffix":""},{"id":522412816,"identity":"22af0d9f-0592-447f-8bea-88648e7fea57","order_by":2,"name":"Ahmed Bashah","email":"","orcid":"","institution":"Dalian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Bashah","suffix":""},{"id":522412817,"identity":"3f9f64ef-b54b-4d26-b66e-b1f0ea00609a","order_by":3,"name":"Ahmed Awad","email":"","orcid":"","institution":"Dalian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Awad","suffix":""}],"badges":[],"createdAt":"2025-09-15 12:45:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7620716/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7620716/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12967-026-07763-5","type":"published","date":"2026-01-29T15:58:03+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93187679,"identity":"2fdd547f-e633-4dd6-a943-24528bf20138","added_by":"auto","created_at":"2025-10-10 03:25:13","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8351,"visible":true,"origin":"","legend":"","description":"","filename":"jtrmJTRMD2516122.xml","url":"https://assets-eu.researchsquare.com/files/rs-7620716/v1/72bf99a237aea595c8c73345.xml"},{"id":93187680,"identity":"be5c4943-0614-4d45-8816-af4061c5e08a","added_by":"auto","created_at":"2025-10-10 03:25:13","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":926,"visible":true,"origin":"","legend":"","description":"","filename":"JTRMD2516122146400.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-7620716/v1/0e104be6318082aaccc9ec16.xml"},{"id":93187681,"identity":"daf5208a-5620-4296-9de6-fc11eb1d85f8","added_by":"auto","created_at":"2025-10-10 03:25:13","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":816,"visible":true,"origin":"","legend":"","description":"","filename":"JTRMD2516122Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-7620716/v1/42672b8092de26635f3712fa.xml"},{"id":101692036,"identity":"81c0888e-7e2a-4dfc-ae41-b9d97988a714","added_by":"auto","created_at":"2026-02-02 16:17:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":473985,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7620716/v1_covered_2d35014a-d8d2-4639-9ea8-5bb57a91fe54.pdf"}],"financialInterests":"","formattedTitle":"Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-translational-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jtrm","sideBox":"Learn more about [Journal of Translational Medicine](http://translational-medicine.biomedcentral.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jtrm/default.aspx","title":"Journal of Translational Medicine","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Artificial intelligence, dental education, medically compromised patients, case-based learning, ChatGPT, Claude, DeepSeek","lastPublishedDoi":"10.21203/rs.3.rs-7620716/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7620716/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Background\n\nArtificial intelligence (AI) has shown remarkable potential in medical education and clinical decision support, yet its role in dentistry—particularly in the management of medically compromised patients—remains largely unexplored. No previous study has systematically benchmarked the performance of advanced large language models (LLMs) in this high-risk domain.\n\nObjective\n\nThis study provides the first comparative evaluation of three LLMs—GPT-5, DeepSeek, and Claude—on multiple-choice questions (MCQs) specifically designed for dental management of medically compromised patients.\n\nMethods\n\nA total of 72 validated MCQs were constructed from the 10th edition of Little \u0026amp; Falace’s Dental Management of the Medically Compromised Patient, covering 18 systemic conditions relevant to dental practice. Each model was independently assessed under identical conditions. Accuracy, agreement with the gold standard answers from the textbook, and error patterns were analyzed.\n\nResults\n\nGPT-5 achieved the highest accuracy (90.28%), followed by Claude (88.89%) and DeepSeek (87.50%) . Performance varied across systemic conditions, with all models demonstrating lower accuracy in complex scenarios such as infective endocarditis and bleeding disorders. Qualitative analysis revealed differences in reasoning depth, error types, and consistency of responses.\n\nConclusions\n\nThis is the first study to benchmark multiple frontier LLMs in dentistry, focusing on medically compromised patients—a group where safe and accurate decision-making is essential. The findings highlight both the promise and limitations of AI in dental education and clinical guidance. By systematically identifying strengths and weaknesses, this work provides an evidence base for integrating LLMs into dental curricula and decision-support systems, while underscoring the need for human oversight in complex medical cases.\n\nClinical significance\n\nGenerative AI models, including GPT-5, DeepSeek, and Claude, demonstrated high accuracy in case-based dental decision-making for medically compromised patients. Their integration could enhance dental education and clinical support. However, variability in performance underscores the need for cautious use and further validation before applying AI tools in complex patient care.","manuscriptTitle":"Performance of GPT-5, DeepSeek, and Claude in Dental MCQs for Medically Compromised Patients","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 03:25:08","doi":"10.21203/rs.3.rs-7620716/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-10-02T22:52:17+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-29T16:56:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-16T13:59:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Translational Medicine","date":"2025-09-15T08:45:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-translational-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jtrm","sideBox":"Learn more about [Journal of Translational Medicine](http://translational-medicine.biomedcentral.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jtrm/default.aspx","title":"Journal of Translational Medicine","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"26c0cb1f-2897-4489-8947-284ab5e13f52","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T16:14:29+00:00","versionOfRecord":{"articleIdentity":"rs-7620716","link":"https://doi.org/10.1186/s12967-026-07763-5","journal":{"identity":"journal-of-translational-medicine","isVorOnly":false,"title":"Journal of Translational Medicine"},"publishedOn":"2026-01-29 15:58:03","publishedOnDateReadable":"January 29th, 2026"},"versionCreatedAt":"2025-10-10 03:25:08","video":"","vorDoi":"10.1186/s12967-026-07763-5","vorDoiUrl":"https://doi.org/10.1186/s12967-026-07763-5","workflowStages":[]},"version":"v1","identity":"rs-7620716","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7620716","identity":"rs-7620716","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}