Classification Performance of General-Purpose Multimodal Large Language Models Across Orthodontic Radiographic Tasks: A Comparative Study of ChatGPT, Gemini, and Claude
Nuri Can Tanrısever, Kutluhan Yılmaz, Ayşegül Dilara Güvenç Tokur, Merve Berika Kadıoğlu, Mahmut Kadıoğlu · 2026
Read Classification Performance of General-Purpose Multimodal Large Language Models Across Orthodontic Radiographic Tasks: A Comparative Study of ChatGPT, Gemini, and Claude by Nuri Can Tanrısever, Kutluhan Yılmaz, Ayşegül Dilara Güvenç Tokur, Merve Berika Kadıoğlu, Mahmut Kadıoğlu (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-13609597.txt.
Description
Nuri Can Tanrısever and co-authors published a 2026 study that put three large chat tools head to head on orthodontic radiograph tasks. Such tools can now read medical images, but how well they classify them for orthodontic care was not known. The study used three kinds of radiograph: side head films, hand and wrist films, and wide panoramic jaw films.
The images came from 250 people, one of each kind per person, for 750 films in all. Two experienced orthodontists set the reference classifications, and each tool read each film once, with the same prompts in Turkish. One tool led on hand and wrist films, at just past four-fifths correct. A second led on panoramic films, at past nine in ten correct. The side head films were the hardest set for all three.
Catalog record
| CREATOR | Nuri Can Tanrısever, Kutluhan Yılmaz, Ayşegül Dilara Güvenç Tokur, Merve Berika Kadıoğlu, Mahmut Kadıoğlu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |