EUVIMEDOpdag EUVIMED
VergleichsstudieOpen access

ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini

Filipe Prazeres iD

JMIR Medical Education · 2025

DOI: 10.2196/65108 ↗

At a glance

Vergleichsstudie in JMIR Medical Education, 2025. Written by Filipe Prazeres. Institution: Faculty of Health Sciences, University of Beira Interior, Av. Infante D. Henrique, Covilhã, 6201-506, Portugal, 351 234393150. Major MEDLINE topics: Educational Measurement, Education, Medical, Clinical Competence. Cited 9 times so far (Crossref); 44 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Advancements in ChatGPT are transforming medical education by providing new tools for assessment and learning, potentially enhancing evaluations for doctors and improving instructional effectiveness.

Objective

This study evaluates the performance and consistency of ChatGPT-3.5 Turbo and ChatGPT-4o mini in solving European Portuguese medical examination questions (2023 National Examination for Access to Specialized Training; Prova Nacional de Acesso à Formação Especializada [PNA]) and compares their performance to human candidates.

Methods

ChatGPT-3.5 Turbo was tested on the first part of the examination (74 questions) on July 18, 2024, and ChatGPT-4o mini on the second part (74 questions) on July 19, 2024. Each model generated an answer using its natural language processing capabilities. To test consistency, each model was asked, “Are you sure?” after providing an answer. Differences between the first and second responses of each model were analyzed using the McNemar test with continuity correction. A single-parameter t test compared the models’ performance to human candidates. Frequencies and percentages were used for categorical variables, and means and CIs for numerical variables. Statistical significance was set at P

Subjects

MeSH terms (MEDLINE)

Educational MeasurementEducation, MedicalClinical CompetenceHumansPortugalNatural Language ProcessingGenerative Artificial Intelligence

Author keywords

AIAI performance evaluationChatGPTChatGPT-3.5 TurboChatGPT-4o miniEuropean PortugueseGPTLLMNLPPortugueseartificial intelligencechatbotevaluationexamination questionlarge language model

Authors and institutions

  • Faculty of Health Sciences, University of Beira Interior, Av. Infante D. Henrique, Covilhã, 6201-506, Portugal, 351 234393150.
  • Family Health Unit Beira Ria, Gafanha da Nazaré, Portugal.
  • CINTESIS@RISE, Department of Community Medicine, Information and Health Decision Sciences, Faculty of Medicine of the University of Porto, Porto, Portugal.

ORCID profiles: Filipe Prazeres

Cite

APA

Prazeres, F. (2025). ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini. JMIR Medical Education. https://doi.org/10.2196/65108

Vancouver

Prazeres F. ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini. JMIR Medical Education. 2025. doi:10.2196/65108

BibTeX
@article{Prazeres2025,
  author = {Prazeres, Filipe},
  title = {ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini},
  journal = {JMIR Medical Education},
  year = {2025},
  doi = {10.2196/65108}
}
Start for free →