Performance of Large Language Models on the Brazilian National Medical Education Examination: Comparative Benchmark Study

Francys de Luca Fernandes da Silva   ^{1 *} , MD ;   Eduardo Augusto Roeder   ^{2 *} , MD ;   João Victor Bruneti Severino   ^{1, 2} , MSc ;   Matheus Nespolo Berger   ² ;   Pedro Angelo Basei de Paula   ² , MD ;   Davi Ferreira   ³ , MD, MSc ;   Maria Han Veiga   ⁴ , PhD ;   Thyago Proença de Moraes   ^{1 *} , MD, PhD ;   Gustavo Lenci Marques   ^{1, 2 *} , MD, PhD

¹ R. Imac. Conceição, 1155 - Prado Velho, Pontifícia Universidade Católica do Paraná, Curitiba, Paraná, Brazil

² Universidade Federal do Paraná, Curitiba, Paraná, Brazil

³ Instituto Tecnológico de Aeronáutica, São José dos Campos, São Paulo, Brazil

⁴ The Ohio State University, Columbus, OH, United States

*these authors contributed equally