Assessing a large language model for glaucoma knowledge: ChatGPT-5 versus residents

Mauro Gobira^1,2; Rodrigo Moreira¹; Flavio J. L. Galhardo Carvalho Filho¹; Kevin Waquim Pessoa Carvalho¹ ; Francisco N. Murta¹ ; Lucas Antônio Avelar Carvalho¹; Rubens Belfort Jr.^1,2; Ivan M. Tavares²

DOI: 10.5935/0004-2749.2025-0283

1. Ophthalmology Department, Instituto da Visão, São Paulo, SP, Brazil
2. Department of Ophthalmology and Visual Sciences, Escola Paulista de Medicina, Universidade Federal de São Paulo, São Paulo, SP, Brazil

Corresponding author

Mauro Gobira
E-mail: [email protected]

Funding: This study received no specific financial support.

Disclosure of potential conflicts of interest: The authors declare no potential conflicts of interest.

Read in Portuguese Print PDF English

How to cite this article:

Gobira^{1 M, 2} , Moreira R, Carvalho Filho FJLG, Carvalho KWP, Murta FN, et al. Assessing a large language model for glaucoma knowledge: ChatGPT-5 versus residents. Arq. Bras. Oftalmol. 2026;89(4):. 10.5935/0004-2749.2025-0283

Export citation