Open journal researchCC BY 4.0

Performance of the Artificial Intelligence large language models ChatGPT 3.5, Gemini (Google Bard), ChatGPT 4.0, and Gemini 2.5 flash in surgical subspecialty questions of Brazilian medical residency exams

Maria Clara Pimenta de Figueiredo; Victor Hugo Alves Diniz; Ana Clara de Campos Granado; Gabriel Chagas Lutfala Paulino; Gabryella Rodrigues de Oliveira

Einstein · Instituto de Ensino e Pesquisa Albert Einstein · Published: 2026-02-16

Journal article in Europe PMC

Read paper Ask paper agent Original DOI Source & full record

The paper agent searches this saved, licensed text and returns exact passages. It does not generate new claims, assess study quality, or replace the original paper. Research settings vary; relevance to school leadership requires editorial judgment.

Read the actionable education leadership companion →

Opening the verified paper and agent…

Checking the article identity, license record, and saved source text.

Open the repository record