Artificial Intelligence Performance in Introductory Biology: Passing Grades but Poor Performance at High Cognitive Complexity

The emergence of Artificial Intelligence (AI) has impacted the world of higher education, and institutions are faced with challenges in integrating AI into curricula. Within the field of biology education, there has been little to no research on AI capabilities to explain collegiate-level biological concepts. In this study, we evaluated the ability of ChatGPT-4, ChatGPT-3.5, Google’s Bard, and Microsoft’s Bing to perform on introductory-level college assessments. All AIs were able to pass the biology course with varying degrees of success related to the usage of image-based assessments. With image-based questions, Bing and Bard received a D− and D, respectively; GPT-3.5 and 4 both received a C−, compared to the average student grade of a B. However, without image-based questions in the assessments, AI scores were a full letter grade higher. Additionally, AI performance was analyzed based on the cognitive complexity of the question, based on Bloom’s Taxonomy of learning. Performance by all four AIs dropped significantly with increasing complex questions, while student performance remained consistent. Overall, this study evaluated the ability of different AIs to perform on collegiate-level biology assessments. By understanding their 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.