Muhammet Cankar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Muhammet Cankar has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Hilal Erdogan
Department of Endodontics, Faculty of Dentistry, Nevsehir Haci Bektas Veli University, Nevşehir, Türkiye
1 shared publication - Taibe Tokgöz Kaplan
Department of Pediatric Dentistry, Faculty of Dentistry, Karabük University, Karabük, Turkey
1 shared publication
Latest Publications
- Open Access
- 22 October 2026
- Published by Springer Nature in BMC Oral Health
Performance of latest-generation large language models on endodontic specialty examination questions: a comparative cross-sectional study
Background: This study aimed to compare the performance of Gemini 3 Pro, Gemini 3 Flash, ChatGPT 5.2, and DeepSeek V3.2 on the Endodontics section of the Turkish Dental Specialty Exam (DUS), with particular attention to question source, type, and endodontic subtopic. Methods: The dataset comprised 187 endodontic questions from 2012–2025, stratified into internet-sourced from 2012–2021 ( n = 127) and textbook-sourced from 2022–2025 ( n = 60). Questions were further categorized by type as case analysis, literature knowledge, combination or visual analysis, and by 10 endodontic subtopics. Following a standardized zero-shot prompting protocol (public web interfaces, default settings, single run per item), two independent endodontic assessors scored responses on a blinded 0–3 rubric, and then the two evaluator scores were averaged for each response. Overall model performance was expressed as a percentage of the maximum possible rubric score (100%). Statistical analysis employed the Friedman test, Wilcoxon Signed-Rank tests with Bonferroni correction, Mann–Whitney U and Kruskal–Wallis tests. Results: All reported percentages represent normalized rubric-based performance scores, evaluating both answer selection and reasoning quality, rather than simple correct/incorrect accuracy rates. High inter-rater agreement was achieved, with quadratic weighted kappa values ranging from 0.954 to 0.998. In overall performance, Gemini 3 Pro (90.37%) and Gemini 3 Flash (88.32%) significantly outperformed ChatGPT 5.2 (78.25%) and DeepSeek V3.2 (62.12%) (adjusted p ≤ 0.001; Kendall’s W = 0.214); corresponding answer accuracies were 94.1%, 93.0%, 86.6%, and 73.3%. No significant difference was found between the Gemini models (adjusted p = 1.000). No significant difference was observed between internet-sourced and textbook-sourced questions within any model. In literature knowledge questions, combination questions, and selected endodontic subtopics, the Gemini models generally showed higher rubric-based performance than the other models. Conclusions: The findings indicate high rubric-based performance of the latest-generation LLMs, particularly the Gemini 3 series, on Turkish endodontics residency examination questions. No significant difference in performance was observed between internet-sourced and textbook-sourced questions; however, contamination of the data in both groups cannot be excluded. These models may serve as adjunctive tools in endodontic education; however, examination performance does not establish clinical diagnostic performance, and their outputs require expert validation.
- 22 October 2026
- Published by Springer Nature in BMC Oral Health
Open AccessPerformance of latest-generation large language models on endodontic specialty examination questions: a comparative cross-sectional study
Background: This study aimed to compare the performance of Gemini 3 Pro, Gemini 3 Flash, ChatGPT 5.2, and DeepSeek V3.2 on the Endodontics section of the Turkish Dental Specialty Exam (DUS), with particular attention to question source, type, and endodontic subtopic. Methods: The dataset comprised 187 endodontic questions from 2012–2025, stratified into internet-sourced from 2012–2021 ( n = 127) and textbook-sourced from 2022–2025 ( n = 60). Questions were further categorized by type as case analysis, literature knowledge, combination or visual analysis, and by 10 endodontic subtopics. Following a standardized zero-shot prompting protocol (public web interfaces, default settings, single run per item), two independent endodontic assessors scored responses on a blinded 0–3 rubric, and then the two evaluator scores were averaged for each response. Overall model performance was expressed as a percentage of the maximum possible rubric score (100%). Statistical analysis employed the Friedman test, Wilcoxon Signed-Rank tests with Bonferroni correction, Mann–Whitney U and Kruskal–Wallis tests. Results: All reported percentages represent normalized rubric-based performance scores, evaluating both answer selection and reasoning quality, rather than simple correct/incorrect accuracy rates. High inter-rater agreement was achieved, with quadratic weighted kappa values ranging from 0.954 to 0.998. In overall performance, Gemini 3 Pro (90.37%) and Gemini 3 Flash (88.32%) significantly outperformed ChatGPT 5.2 (78.25%) and DeepSeek V3.2 (62.12%) (adjusted p ≤ 0.001; Kendall’s W = 0.214); corresponding answer accuracies were 94.1%, 93.0%, 86.6%, and 73.3%. No significant difference was found between the Gemini models (adjusted p = 1.000). No significant difference was observed between internet-sourced and textbook-sourced questions within any model. In literature knowledge questions, combination questions, and selected endodontic subtopics, the Gemini models generally showed higher rubric-based performance than the other models. Conclusions: The findings indicate high rubric-based performance of the latest-generation LLMs, particularly the Gemini 3 series, on Turkish endodontics residency examination questions. No significant difference in performance was observed between internet-sourced and textbook-sourced questions; however, contamination of the data in both groups cannot be excluded. These models may serve as adjunctive tools in endodontic education; however, examination performance does not establish clinical diagnostic performance, and their outputs require expert validation.
- Top Cited Papers
- 2 November 2024
- Published by Wiley in Dental Traumatology
- Vol. 41 (2) , 178-186
Evidence‐Based Potential of Generative Artificial Intelligence Large Language Models on Dental Avulsion: ChatGPT Versus Gemini
Background: In this study, the accuracy and comprehensiveness of the answers given to questions about dental avulsion by two artificial intelligence‐based language models, ChatGPT and Gemini, were comparatively evaluated.Materials and Methods: Based on the guidelines of the International Society of Dental Traumatology, a total of 33 questions were prepared, including multiple‐choice questions, binary questions, and open‐ended questions as technical questions and patient questions about dental avulsion. They were directed to ChatGPT and Gemini. Responses were recorded and scored by four pediatric dentists. Statistical analyses, including ICC analysis, were performed to determine the agreement and accuracy of the responses. The significance level was set as p < 0.050.Results: The mean score of the Gemini model was statistically significantly higher than the ChatGPT (p = 0.001). ChatGPT gave more correct answers to open‐ended questions and T/F questions on dental avulsion; it showed the lowest accuracy in the MCQ section. There was no significant difference between the responses of the Gemini model to different types of questions on dental avulsion and the median scores (p = 0.088). ChatGPT and Gemini were analyzed with the Mann–Whitney U test without making a distinction between question types, and Gemini answers were found to be statistically significantly more accurate (p = 0.004).Conclusions: The Gemini and ChatGPT language models based on the IADT guideline for dental avulsion undoubtedly show promise. To guarantee the successful incorporation of LLMs into practice, it is imperative to conduct additional research, clinical validation, and improvements to the models.
- 2 November 2024
- Published by Wiley in Dental Traumatology
- Vol. 41 (2) , 178-186
Top Cited PapersEvidence‐Based Potential of Generative Artificial Intelligence Large Language Models on Dental Avulsion: ChatGPT Versus Gemini
Background: In this study, the accuracy and comprehensiveness of the answers given to questions about dental avulsion by two artificial intelligence‐based language models, ChatGPT and Gemini, were comparatively evaluated.Materials and Methods: Based on the guidelines of the International Society of Dental Traumatology, a total of 33 questions were prepared, including multiple‐choice questions, binary questions, and open‐ended questions as technical questions and patient questions about dental avulsion. They were directed to ChatGPT and Gemini. Responses were recorded and scored by four pediatric dentists. Statistical analyses, including ICC analysis, were performed to determine the agreement and accuracy of the responses. The significance level was set as p < 0.050.Results: The mean score of the Gemini model was statistically significantly higher than the ChatGPT (p = 0.001). ChatGPT gave more correct answers to open‐ended questions and T/F questions on dental avulsion; it showed the lowest accuracy in the MCQ section. There was no significant difference between the responses of the Gemini model to different types of questions on dental avulsion and the median scores (p = 0.088). ChatGPT and Gemini were analyzed with the Mann–Whitney U test without making a distinction between question types, and Gemini answers were found to be statistically significantly more accurate (p = 0.004).Conclusions: The Gemini and ChatGPT language models based on the IADT guideline for dental avulsion undoubtedly show promise. To guarantee the successful incorporation of LLMs into practice, it is imperative to conduct additional research, clinical validation, and improvements to the models.