Comparative Performance of Large Language Models on European Gastroenterology Board-Style Questions: Analysis of Reasoning Versus Non-Reasoning Architectures
: This benchmarking study demonstrates that current LLMs, particularly those with reasoning architectures, achieve high accuracy on European gastroenterology board-style questions. However, significant performance gaps in specific domains highlight limitations that must be addressed before clinical application. These findings provide a baseline for evaluating LLM capabilities in European medical contexts.
Authors
- Manuel Lehner
- Cesare Hassan (ORCID: https://orcid.org/0000-0001-7167-1459)
- Jan Krivinka
- Petr Vaněk (ORCID: https://orcid.org/0000-0001-9573-5277)
- Hakan Aydinli
- Henriette H. Heinrich
- Sara Schiavone
- Cem Simsek
Institutions
- University of Minnesota (US)
- Humanitas University (IT)
- University of Basel (CH)
- Masaryk University (CZ)
- University Hospital Brno (CZ)
- University Hospital Olomouc (CZ)
- Masaryk Memorial Cancer Institute (CZ)
- University of Minnesota Medical Center (US)
- IRCCS Humanitas Research Hospital (IT)
- Hacettepe University (TR)
- Palacký University Olomouc (CZ)
Publication Details
- Journal
- Journal of Clinical Medicine
- Published
- 2026-04-02
- DOI
- https://doi.org/10.3390/jcm15072692
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00