Clinical Knowledge and Reasoning Abilities of AI Large Language Models in Anesthesiology: A Comparative Study on the American Board of Anesthesiology Examination

CONCLUSIONS: GPT-4 outperformed GPT-3 and Bard on both basic and advanced sections of the written ABA examination, and actual board examiners considered GPT-4 to have a reasonable possibility of passing the real oral examination; these models also exhibit varying degrees of proficiency across distinct topics.PMID:38640076 | DOI:10.1213/ANE.0000000000006892
Source: Anesthesia and Analgesia - Category: Anesthesiology Authors: Source Type: research