FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
This provides a rigorous testbed for quantifying AI progress toward expert-level mathematical abilities, addressing a gap in evaluation for the AI research community.
The authors tackled the problem of evaluating advanced mathematical reasoning in AI by introducing FrontierMath, a benchmark of hundreds of original, challenging mathematics problems, and found that current state-of-the-art AI models solve under 2% of these problems.
We introduce FrontierMath, a benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians. The questions cover most major branches of modern mathematics -- from computationally intensive problems in number theory and real analysis to abstract questions in algebraic geometry and category theory. Solving a typical problem requires multiple hours of effort from a researcher in the relevant branch of mathematics, and for the upper end questions, multiple days. FrontierMath uses new, unpublished problems and automated verification to reliably evaluate models while minimizing risk of data contamination. Current state-of-the-art AI models solve under 2% of problems, revealing a vast gap between AI capabilities and the prowess of the mathematical community. As AI systems advance toward expert-level mathematical abilities, FrontierMath offers a rigorous testbed that quantifies their progress.