Associate Professor of Biology Natalie Nannas is the senior author of a paper published recently by the MDPI journal, Education Sciences. “Artificial Intelligence Performance in Introductory Biology: Passing Grades but Poor Performance at High Cognitive Complexity” is the result of a study conducted by 2025 graduates Megan Rai and Michael Ngaw in which they “investigated the ability of four different AIs to perform on [an] assessment from introductory biology.” The course, BIO100, focuses on the key concepts of evolution, information flow, transformation of energy and matter, structure and function, and biological interactions.
The study evaluated the performance of ChatGPT-4, ChatGPT-3.5, Google’s Bard, and Microsoft’s Bing. The results showed that all of the AI products were able to pass the biology course “with varying degrees of success related to the usage of image-based assessments.” Overall, AI received grades ranging from D- to C-, while the average student grade was a B. However, on assessments that did not include image-based questions, the study showed AI scored a full letter grade higher.
“By understanding [AI’s] capabilities at different levels of complexity, educators will be better able to adapt assessments based on AI ability, particularly through the utilization of image- and sequence-based questions, and integrate AI into higher education curricula,” the researchers concluded.
Posted November 18, 2025
