Key numbers on the growth and impact of AI
Data on AI models, data centers, companies, and more
Model performance on key benchmarks
A benchmark of several hundred unpublished, highly challenging mathematics problems. Difficulty Tiers 1-3 cover undergraduate through early postdoc level problems, while Tier 4 is research-level mathematics.
This project is supported by OpenAI.
Have a question? Noticed something wrong? Let us know.
If you would like a reply, please include your name and email address.
FrontierMath Tiers 1-4 is an AI benchmark of hundreds of unpublished and extremely challenging math problems.