Comparative analysis of the performance of large language models in answering endodontics questions on the dental specialty exam
Journal of Health Sciences and Medicine · 19.05.2026 · 9 (3) · 767-773
DOI: 10.32322/jhsm.1902303 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Health Sciences and Medicine, online erschienen am 19.05.2026. Verfasst von Gizem Fatma Özden und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben.
Abstract (Originalsprache)
Aims
The aim of this study was to compare the accuracy of ChatGPT (GPT-5), Gemini (Gemini 2.5 Pro), and Grok (SuperGrok) on Dental Specialty Exam (DUS) endodontics questions and to examine differences by exam year and item format (text-based vs figure-based).
Methods
Endodontics questions from Turkish Assessment, Selection and Placement Center (ÖSYM) DUS exams (2012-2021) were reviewed. Of 130 questions, three items officially canceled by ÖSYM were excluded, leaving 127 questions (122 text-based, 5 figure-based). Figure-based items included periapical radiographs, clinical photographs, or schematic diagrams. Questions were submitted to each model using default settings with one response per item; no tuning or repeat runs were performed. Responses were scored as correct/incorrect using the official answer key. Fisher’s exact test and, when required, Monte Carlo-corrected Fisher’s exact test were applied (p
Zitieren
APA
Özden, G. F., & Şahin, E. N. (2026). Comparative analysis of the performance of large language models in answering endodontics questions on the dental specialty exam. Journal of Health Sciences and Medicine, 9(3), 767-773. https://doi.org/10.32322/jhsm.1902303
Vancouver
Özden GF, Şahin EN. Comparative analysis of the performance of large language models in answering endodontics questions on the dental specialty exam. Journal of Health Sciences and Medicine. 2026;9(3):767-773. doi:10.32322/jhsm.1902303
BibTeX
@article{zden2026,
author = {Özden, Gizem Fatma and Şahin, Elyase Nur},
title = {Comparative analysis of the performance of large language models in answering endodontics questions on the dental specialty exam},
journal = {Journal of Health Sciences and Medicine},
year = {2026},
volume = {9},
number = {3},
pages = {767--773},
doi = {10.32322/jhsm.1902303}
}
EUVIMED