On December 24, Jin Shi Data News, recently, medical and AI experts from top universities and institutions such as Harvard University jointly conducted a study to evaluate the performance of the o1-preview model under OpenAI in medical reasoning tasks. The results show that the model performs excellently in multiple tasks, even reaching superhuman levels, with a diagnostic accuracy of nearly 80%.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Harvard and Stanford's latest research: the diagnostic accuracy of the o1-preview model is as high as nearly 80%.
On December 24, Jin Shi Data News, recently, medical and AI experts from top universities and institutions such as Harvard University jointly conducted a study to evaluate the performance of the o1-preview model under OpenAI in medical reasoning tasks. The results show that the model performs excellently in multiple tasks, even reaching superhuman levels, with a diagnostic accuracy of nearly 80%.