Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 23, 2026

Performance of Large Language Models on Official Periodontology Questions: A 13-Year Analysis of the Turkish Dental Specialization Examination

View Full Paper
Ask AI
Bookmark
Share

Authors

YEYaren ErişkenFKFatih Karaaslan

Discussion

Loading...

Member takes

Overview

Performance analysis of multiple-choice questions shows significant model dependency in periodontology, implying educational potential and critical reasoning gaps.

Key Points

  • This research evaluates the performance of large language models on periodontology questions.
  • Analyzed 180 text-based questions from the Turkish Dental Specialization Examination over 13 years.
  • Tested eight large language models on the categorized questions via official interfaces.
  • Compared accuracy across models, domains, and question types using Pearson’s chi-square test.
  • Gemini 2.5 Pro showed the highest performance with 100% accuracy in six domains.
  • Accuracy varied significantly by domain with a Cramér’s V of .163.
  • Underperforming models included ChatGPT-4o mini and Qwen 2.5-Max, particularly in Periodontium and Periodontal Treatment.

Cite This Study

Erişken et al. (2025) studied this question.

synapsesocial.com/papers/699ba09872792ae9fd870834https://doi.org/10.31067/acusaglik.1816444
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Benchmarking large language models on Turkish dental specialty examination questions: effects of model, discipline, and question format2026
  2. 2Performance of large language models in a high-stakes dental assessment: evidence from the Turkish dentistry specialization examination2026
  3. 3A comparative analysis of the performance of leading large language models on the endodontics section of the dentistry specialization exam in Türkiye2026
  4. 4Comparative analysis of the performance of artificial intelligence language models on Turkish dental specialty examination questions2026
  5. 5Evaluating large language models using national endodontic specialty examination questions: are they ready for real-world dentistry?2025 · 20 citations