FrontierMath
Progress Over Time
Interactive timeline showing model performance evolution on FrontierMath
FrontierMath Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  OpenAI | — | 1.1M | $5.00 / $30.00 | ||
| 2 | OpenAI | — | 1.1M | $2.00 / $12.00 | ||
| 3 | OpenAI | — | 1.1M | $0.20 / $1.20 | ||
| 4 | OpenAI | — | 1.0M | $2.50 / $15.00 | ||
| 5 | OpenAI | — | 400K | $1.75 / $14.00 | ||
| 6 | OpenAI | — | — | — | ||
| 7 | OpenAI | — | 1.1M | $5.00 / $30.00 | ||
| 8 | OpenAI | — | 400K | $1.25 / $10.00 | ||
| 8 | OpenAI | — | 400K | $1.25 / $10.00 | ||
| 8 | OpenAI | — | — | — | ||
| 11 | OpenAI | — | — | — | ||
| 12 | OpenAI | — | 400K | $0.25 / $2.00 | ||
| 13 | OpenAI | — | — | — | ||
| 14 | OpenAI | — | — | — | ||
| 15 | OpenAI | — | — | — | ||
| 16 |  Microsoft | — | — | — | ||
| 17 | OpenAI | — | — | — |
Sub-benchmarks
What is FrontierMath?
A benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians, covering most major branches of modern mathematics from number theory and real analysis to algebraic geometry and category theory.
FrontierMath is a text benchmark evaluating models on math and reasoning tasks. LLM Stats tracks 17 models on this benchmark, scored on a 0–1 scale. The current average is 0.3, with the leader at 0.9.
Compare leaders on the best AI for math and best AI for reasoning leaderboards.
Current leaders
GPT-5.6 Sol from OpenAI currently leads the FrontierMath leaderboard with a score of 0.890 across 17 evaluated AI models.
Source paper
- Title
- FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
- Authors
- Elliot Glazer, Ege Erdil, Tamay Besiroglu, Diego Chicharro, and 20 others
- Published
- arXiv
- 2411.04872
Abstract
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 FrontierMath uses new, unpublished problems and automated verification to reliably evaluate models while minimizing risk of data contamination.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.
FAQ
Common questions about the FrontierMath benchmark and leaderboard.