ChatGPT clears US Medical Licensing Exam: Study
1 year, 10 months ago

ChatGPT clears US Medical Licensing Exam: Study

The Hindu  

ChatGPT could score at or around the approximately 60% passing threshold for the United States Medical Licensing Exam, with responses that made coherent, internal sense and contained frequent insights, according to a new study. Tiffany Kung and colleagues at AnsibleHealth, California, US, tested ChatGPT's performance on the USMLE, a highly standardized and regulated series of three exams, including Steps 1, 2CK, and 3, required for medical licensure in the US, the study said. The authors found that after indeterminate responses were removed, ChatGPT had scored between 52.4 per cent and 75 per cent across the three USMLE exams, the study published in the journal PLOS Digital Health said. ChatGPT also exceeded the performance of PubMedGPT, a counterpart model trained exclusively on biomedical domain literature, which scored 50.8% on an older dataset of USMLE-style questions, the study said.

History of this topic

Can ChatGPT be used for medical treatment? Here's what expert says
1 year, 8 months ago
AI Calling: ChatGPT Passes Mock Medical Exam, GPT-4 Outperforms Other Users, Reveals Latest Study
1 year, 8 months ago
Medical, law, coding, and 4 other exams that ChatGPT managed to crack easily
1 year, 10 months ago
ChatGPT clears US Medical Licensing Exam: Study
1 year, 10 months ago
The AI doctor will see you now: ChatGPT passes gold-standard US medical exam
1 year, 10 months ago
ChatGPT model passes medical, law exams, with human help
1 year, 10 months ago

Discover Related