ORIGINAL RESEARCH article
Front. Oral Health
Sec. Oral Health Promotion
This article is part of the Research TopicReimagining Artificial Intelligence in Oral Health: Human-Centered Approaches for Equitable HealthcareView all articles
Performance of Five Free Large Language Models in Dental Trauma: A 30-Day Longitudinal Benchmark Study
Provisionally accepted
Rafaela Mancini Lisboa1Arian Braido2Adriana de-Jesus-Soares2
Nitesh Tewari3Carlos José Soares4
Luiz Renato Paranhos5*Walbert A. Vieira1- 1Centro Universitario das Faculdades Associadas de Ensino, São João da Boa Vista, Brazil
- 2Universidade Estadual de Campinas Faculdade de Odontologia de Piracicaba, Piracicaba, Brazil
- 3All India Institute of Medical Sciences New Delhi Department of Radiodiagnosis, New Delhi, India
- 4Universidade Federal de Uberlandia, Uberlândia, Brazil
- 5Federal University of Uberlandia, Uberlândia, Brazil
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Objective: To compare the accuracy and consistency of five large language models (LLMs) in generating responses about dental trauma. Materials and Methods: Sixty dichotomous (true/false) questions were submitted daily to each LLM (ChatGPT, Google Gemini, Microsoft Copilot, DeepSeek, and Meta AI) for 30 days, totaling 18,000 responses. All interactions were performed under two prompting conditions (zero-shot and zero-shot with context). LLM responses were compared against the International Association of Dental Traumatology (IADT) guidelines. Formatado: Português (Brasil) This is a provisional file, not the final typeset article Statistical analysis was conducted using a generalized linear mixed model (GLMM) with a binomial distribution (α = 0.05), alongside calculation of sensitivity, specificity, accuracy, and area under the ROC curve (AUC) based on the 60-item set. Temporal stability was assessed using the intraclass correlation coefficient ICC.. Results: All LLMs achieved accuracy above 85%, with Microsoft Copilot (91.1%) and DeepSeek (90%) performing best; no significant difference was observed between them (p > 0.05), but both outperformed the other models (p < 0.05). DeepSeek and Microsoft Copilot also showed the highest consistency over 30 days (ICC > 0.90). Conclusion: All evaluated LLMs, particularly Copilot and DeepSeek, demonstrated high accuracy in providing information on dental trauma, with stable performance over time. While the use of a context prompt did not significantly affect accuracy or stability.
Keywords: artificial intelligence, Chatbot, dental trauma, Large language models, traumatic dental injuries
Received: 01 Nov 2025; Accepted: 30 Nov 2025.
Copyright: © 2025 Lisboa, Braido, de-Jesus-Soares, Tewari, Soares, Paranhos and Vieira. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Luiz Renato Paranhos
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.