What question did this study set out to answer?

February 16, 2023Open Access

ChatGPT Performs on the Chinese National Medical Licensing Examination

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial compares ChatGPT's knowledge and interpretation ability with that of medical students, suggesting room for improvement.

The study aims to evaluate how well ChatGPT performs on the Chinese National Medical Licensing Examination compared to medical students.
Administered the Chinese National Medical Licensing Examination to ChatGPT and medical students.
Evaluated exam performance over two years consisting of four exam units.
Compared results from ChatGPT with five-year medical students.
ChatGPT’s performance was lower than that of medical students.
ChatGPT had a correct answer rate influenced by the year of the exam questions.
Indications that ChatGPT's performance may improve with further development in deep learning.

Wang et al. (2023) studied this question.

View Full Paper

Ask AI

Bookmark