A comparative analysis of the performance of leading large language models on the endodontics section of the dentistry specialization exam in Türkiye
PLOS One · 01.06.2026 · 21 (6) · e0350457
DOI: 10.1371/journal.pone.0350457 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 01.06.2026. Verfasst von Beyhan Başkan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Endodontics, Faculty of Dentistry, Kahramanmaraş Sütçü İmam University, Kahramanmaras, Türkiye. Hauptthemen laut MEDLINE: Large Language Models, Endodontics, Educational Measurement, Education, Dental. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objective
This study aimed to evaluate and compare the performance of eight contemporary LLMs on the endodontics section of the DUS, assessing their accuracy in both theoretical knowledge and simulated clinical scenarios from historical exam data.
Methods
The performance of eight different large language models (Claude 4, DeepSeek V3, Gemini 2.5 Pro, ChatGPT-4o, ChatGPT-5, Grok 4, LLaMA 4, and Perplexity) was evaluated using 127 multiple-choice endodontics questions from the Specialization Exam in Dentistry (DUS) administered by the Student Selection and Placement Center (ÖSYM) between 2012 and 2021. The models’ responses were compared against the official answer keys. Statistical analyses were performed using Pearson’s chi-square and McNemar tests, with a significance level of α = 0.05.
Results
Significant differences existed among LLMs in overall accuracy (p < 0.001). Gemini 2.5 Pro achieved the highest accuracy (90.6%), outperforming ChatGPT-4o (61.4%) and LLaMA 4 (71.7%). In Clinical Practice Questions (CPQ), Gemini 2.5 Pro (93.9%) surpassed ChatGPT-4o (57.6%; p = 0.019). For General Knowledge and Concept Questions (GKCQ), Gemini 2.5 Pro (89.4%), Grok 4 (85.1%), and DeepSeek V3 (84.0%) exceeded ChatGPT-4o (62.8%; p < 0.001). No significant intra-model differences emerged between CPQ and GKCQ performance (p > 0.05).
Conclusion
Contemporary LLMs demonstrate substantial competence in endodontic knowledge, with Gemini 2.5 Pro excelling in both theoretical and clinical queries. However, significant performance variability across models (61.4%−90.6%) and the complexity of retrieving and resolving clinical exam queries necessitate domain-specific optimization and expert oversight for reliable integration into dental education and practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Endodontics, Faculty of Dentistry, Kahramanmaraş Sütçü İmam University, Kahramanmaras, Türkiye.
- Department of Pediatric Dentistry, Faculty of Dentistry, Kahramanmaraş Sütçü İmam University, Kahramanmaras, Türkiye.
- Department of Endodontics, Faculty of Dentistry, Niğde Ömer Halisdemir University, Nigde, Türkiye.
ORCID-Profile: Beyhan Başkan
Zitieren
APA
Başkan, B., Başkan, H. K., & Koç, N. (2026). A comparative analysis of the performance of leading large language models on the endodontics section of the dentistry specialization exam in Türkiye. PLOS One, 21(6), e0350457. https://doi.org/10.1371/journal.pone.0350457
Vancouver
Başkan B, Başkan HK, Koç N. A comparative analysis of the performance of leading large language models on the endodontics section of the dentistry specialization exam in Türkiye. PLOS One. 2026;21(6):e0350457. doi:10.1371/journal.pone.0350457
BibTeX
@article{Bakan2026,
author = {Başkan, Beyhan and Başkan, Hatice Kübra and Koç, Nevzat},
title = {A comparative analysis of the performance of leading large language models on the endodontics section of the dentistry specialization exam in Türkiye},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0350457},
doi = {10.1371/journal.pone.0350457}
}
EUVIMED