Accuracy of large language models in the Turkish dental specialization examination (DUS): a multidimensional evaluation across disciplines and question formats

Fatih Karaaslan, Muhammed Halil Yilan, Merve Tirimoğulları · 2026

Read Accuracy of large language models in the Turkish dental specialization examination (DUS): a multidimensional evaluation across disciplines and question formats by Fatih Karaaslan, Muhammed Halil Yilan, Merve Tirimoğulları (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/pmc-13632068.txt.

Description

Fatih Karaaslan, Muhammed Halil Yilan, and Merve Tirimoğulları test in a 2026 study how well chatbots answer a Turkish dental exam. They fed over a thousand past exam questions, in three formats and eight fields, to seven chat tools, once each. The questions came from exams held between 2012 and 2021.

Scores split widely. The top tool got nearly ninety-three of each hundred right, while the lowest got under sixty. Gaps showed in every field and format, though one format had few items and so gave a shakier read. Tools of this kind, the team notes, are far from equal on specialist tests.

Catalog record

CREATORFatih Karaaslan, Muhammed Halil Yilan, Merve Tirimoğulları
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE41 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13632068

Browse the full library · About the Tower of Babel