This paper is in the following e-collection/theme issue:

Generative Language Models Including ChatGPT (521) AI Language Models in Health Care (112) Learning and Education (90) Artificial Intelligence (1776) Applications of AI (181)

Published on in Vol 27 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/65146, first published .
Unveiling GPT-4V's hidden challenges behind high accuracy on USMLE questions: Observational Study

Unveiling GPT-4V's hidden challenges behind high accuracy on USMLE questions: Observational Study

Unveiling GPT-4V's hidden challenges behind high accuracy on USMLE questions: Observational Study

Authors of this article:

Zhichao Yang1 Author Orcid Image ;   Zonghai Yao1 Author Orcid Image ;   Mahbuba Tasmin1 Author Orcid Image ;   Parth Vashisht1 Author Orcid Image ;   Won Seok Jang2 Author Orcid Image ;   Feiyun Ouyang2 Author Orcid Image ;   Beining Wang3 Author Orcid Image ;   David McManus4 Author Orcid Image ;   Dan Berlowitz5, 6 Author Orcid Image ;   Hong Yu1, 2, 6, 7 Author Orcid Image
Article Authors Cited by (3) Tweetations Metrics
All Time | Last Month | Last Six Months | Last Year
There are currently no tweets available for this article within the specified range.