Generative AI performance in core undergraduate mathematics: a curriculum-level case study

A study investigated the performance of Generative AI (GenAI) tools, such as OpenAI's ChatGPT, on core undergraduate mathematics assessments. The research utilized existing examination questions as a proxy for course content, applying an empirical approach to generate, transcribe, and blind-mark GenAI submissions across eight first-year mathematics assessments. This research is part of a broader re-evaluation of traditional assessment practices and the exploration of alternatives to in-person, closed-book examinations in higher education.

The integration and performance of GenAI in academic settings necessitate a re-evaluation of educational strategies and assessment methodologies. Understanding GenAI capabilities across core curricula is crucial for maintaining academic integrity, ensuring pedagogical effectiveness, and preparing institutions for technological shifts in learning and evaluation.

Generative AI tools are impacting educational assessment paradigms.

Forward consideration, not a verified fact.