ChatGPT Model Excels in Neurology Exam, Surpassing Human Student Level
站长之家
44
In a recent study published in the JAMANetworkOpen journal, researchers assessed the performance of two ChatGPT large language models in answering questions from the American Board of Psychiatry and Neurology question bank. One model achieved an accuracy of 85% in the exam, surpassing the average performance of human neuroscience students. These models hold significant potential for widespread application in clinical neurology.
© Copyright AIbase Base 2024, Click to View Source - https://www.aibase.com/news/4058