Publications & Commentary
Publications Gradient Updates Epoch After Hours
Data & Resources
Datasets
Overview AI Benchmarking Notable AI Models Large-Scale AI Models ML Hardware AI Supercomputers
Resources
AI Trends & Statistics Data Insights
Projects
FrontierMath GATE Playground Distributed Training Model Counts
About
Our Team About Our Research Careers Partner With Us Our Funding Donate
Contact

FrontierMath — benchmarking AI against advanced mathematical research

A benchmark of several hundred unpublished, expert-level mathematics problems that takes specialists hours to days to solve. Difficulty Tiers 1-3 cover undergraduate through early graduate level problems, while Tier 4 is research-level mathematics. This project is supported by OpenAI.

Learn more Sample problems
Thank you for your feedback!

Your comment will be reviewed. We may not be able to respond to every submission.