ChatGPT has passed the US Medical exam and Wharton’s MBA test

The researchers for the paper available on medRxivopens wrote that “ChatGPT demonstrated a high level of concordance and insight in its explanations. These results suggest that large language models may have the potential to assist with medical education, and potentially, clinical decision-making.”

As part of the testing, the researchers relied on 376 publicly-available test questions from June 2022 sample exam, and relied on “random spot checking” to ensure that “none of the answers, explanations, or related content were indexed on Google prior to January 1, 2022.” Right now ChatGPT’s learning dataset is limited to 2021, as the company also notes.

In another interesting case, ChatGPT has managed to pass an MBA exam designed by a professor of Wharton from the University of Pennsylvania. The ChatGPT-3 powered chatbot has passed the final exam of the MBA course scoring between a B- and B grade.

According to the report, the ChatGPT bot has an “amazing job at basic operations management and process analysis questions including those that are based on case studies,” with excellent explanation. The bot was also said to be good at “modifying its answers in response to human hints.”

According to educators, ChatGPT’s response style makes it difficult to distinguish it from human responses. Experts in artificial intelligence and educators suggest that products like ChatGPT might pose a negative effect on the education system in future while some are not at all concerned about it.