Performance of GPT-4o and o1-Pro on United Kingdom Medical Licensing Assessment-style items: a comparative study
ChatGPT shows strong potential as an adjunct learning tool for UKMLA preparation, with both models achieving scores above the calculated pass mark. This underscores the promise of advanced AI models in medical education. However, specialty-specific inconsistencies suggest AI tools should complement, rather than replace, traditional study methods.
Authors
- Mahsa Zolfaghari (ORCID: https://orcid.org/0000-0003-3547-4428)
- Anizana Ahmad
- Behrad Vakili
Institutions
- St Thomas' Hospital (GB)
- University of Staffordshire (GB)
- Guy's and St Thomas' NHS Foundation Trust (GB)
- Buckinghamshire Healthcare NHS Trust (GB)
Publication Details
- Journal
- Journal of Educational Evaluation for Health Professions
- Published
- 2025-10-10
- DOI
- https://doi.org/10.3352/jeehp.2025.22.30
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00