LLMs' Capabilities at the High School Level in Chemistry: Cases of ChatGPT and Microsoft Bing Chat

20 June 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


This study evaluates the potential and challenges of large langue models (LLMs) for education in chemistry. Specifically, we analyze the performance of two state -of-the art of LLMs, ChatGPT and Microsoft Bing AI Chat, on a quiz dataset consisting of 200 multiple-choice questions in chemistry at the high school level. The results show that ChatGPT and Microsoft Bing AI Chat have limitations in answering questions at the application and high application levels. We also compare the scores of the LLMs models with Vietnamese students, indicating that their performance is still lower than the ability of Vietnamese students. The findings suggest that LLMs have great potential in assisting learning and teaching, but further development is needed to improve their ability to solve complex questions at the high application level.


Bing Chat
large language models
chemistry education
performance evaluation.

Supplementary weblinks


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.