ArticleEinstein (Sao Paulo, Brazil)2026
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 et al.PubMed ↗Full text ↗Publisher ↗
No numbers read from the abstract.