Comparative assessment of the accuracy of different artificial intelligence models in answering analytical and knowledge-based questions in oral and maxillofacial radiology and oral and maxillofacial surgery
Erçin Samunahmetoglu, Arzum Yilmaz · 2026
Read Comparative assessment of the accuracy of different artificial intelligence models in answering analytical and knowledge-based questions in oral and maxillofacial radiology and oral and maxillofacial surgery by Erçin Samunahmetoglu, Arzum Yilmaz (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13617685.txt.
Description
Erçin Samunahmetoglu and Arzum Yilmaz compare five artificial intelligence models on dentistry exam questions in a 2026 study. They used two hundred fifty-eight multiple-choice questions from the Turkish Dental Specialty Examination held between 2012 and 2021, split between factual knowledge items and harder analytical ones in oral radiology and surgery. Each model answered every question once under default settings.
Accuracy differed significantly between models overall and on both question types. Gemini scored highest on knowledge questions, while Claude scored lowest, and no model clearly beat the others on analytical questions in head-to-head checks. Agreement between models was low by one measure and moderate by another. Overall success mostly mirrored factual recall, leading the authors to conclude that these systems recall dental facts well but reason clinically less reliably. That suits them as study supports rather than independent decision makers.
Catalog record
| CREATOR | Erçin Samunahmetoglu, Arzum Yilmaz |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45655 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |