Free-tier Large Language Models on the MATH Benchmark: Implications for AI Literacy Instruction
Manuscript under review; submitted to the AERA 2027 annual meeting
Sam Gilson
Manuscript under review
Summary
This manuscript examines the mathematical performance of models available through free access tiers and considers what capability evidence could contribute to AI literacy instruction. The instructional question is how students might use evidence about a tool’s strengths and limitations when deciding what to check.
What this study can tell us
The manuscript is under review, and its full text is not available on this site. This page is a project description, not a published paper record. Detailed results and a formal citation will be added when a public manuscript or publication is available.
Concepts used in this work
Free-tier accessible model · Structured unevenness · Calibrated trust