Accuracy of Large Language Models in Answering Dental Examination Questions: A Systematic Review and Meta-Analysis
Mahmood Dashti, Farshad Khosraviani, Atieh Meyari, Mohammad Hosein Amirzade-Iranaq, Akhilanand Chaurasia, Delband Hefzi, Niloofar Ghadimi, Antonin Tichy, Zohaib Khurshid, Falk Schwendicke · 2026
Read Accuracy of Large Language Models in Answering Dental Examination Questions: A Systematic Review and Meta-Analysis by Mahmood Dashti, Farshad Khosraviani, Atieh Meyari, Mohammad Hosein Amirzade-Iranaq, Akhilanand Chaurasia, Delband Hefzi, Niloofar Ghadimi, Antonin Tichy, Zohaib Khurshid, Falk Schwendicke (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-13202568.txt.
Description
Mahmood Dashti and a team of co-authors pool studies on how well large language models answer dental exam questions, in a review dated twenty twenty-six. Such models are now used in health and dental teaching, but their skill on expert tests was unclear. The team searched four databases and gathered data on model versions and score rates. Thirty-nine studies were found in total.
Across studies, the models scored about sixty-four percent on average, with wide spread between them. ChatGPT-4 and one rival tool scored highest, near three quarters right. Newer versions beat older ones in direct matches. The authors say the tools are not fit to make care choices alone but may help in teaching when their limits are kept in view.
Catalog record
| CREATOR | Mahmood Dashti, Farshad Khosraviani, Atieh Meyari, Mohammad Hosein Amirzade-Iranaq, Akhilanand Chaurasia, Delband Hefzi, Niloofar Ghadimi, Antonin Tichy, Zohaib Khurshid, Falk Schwendicke |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |