- Organizations
- ETH Zurich SRI Lab
ETH Zurich SRI Lab: AI benchmarks & research
ETH Zurich Secure, Reliable and Intelligent Systems Lab. Runs MathArena and the USAMO proof evaluations.
Maintained by ETH Zurich SRI Lab
4 benchmarks- IMOProof-Adv
IMOProof-Adv is an advanced benchmark of International Mathematical Olympiad-style proof problems requiring rigorous multi-step mathematical proofs.
- Leader
Seed 2.1 Pro54.3%- Models scored
- 1
- MathArena Apex
MathArena Apex is a challenging math contest benchmark featuring the most difficult mathematical problems designed to test advanced reasoning and problem-solving abilities of AI models. It focuses on olympiad-level mathematics and complex multi-step mathematical reasoning.
- Leader
DeepSeek-V4-Pro-Max90.2%
- Models scored
- 11
- USAMO 2026
USAMO 2026 evaluates models on the six problems from the 2026 United States of America Mathematical Olympiad, requiring rigorous proof-based reasoning. Following the MathArena methodology, proofs are graded against human expert rubrics by dual strong judge models, with the minimum of the two scores taken as final. Maximum score is 42 points.
- Leader
MiniMax M336- Models scored
- 3
- USAMO25
The 2025 United States of America Mathematical Olympiad (USAMO) benchmark consists of six challenging mathematical problems requiring rigorous proof-based reasoning. USAMO is the most prestigious high school mathematics competition in the United States, serving as the final round of the American Mathematics Competitions series. This benchmark evaluates models on mathematical problem-solving capabilities beyond simple numerical computation, focusing on formal mathematical reasoning and proof generation.
- Leader
Claude Mythos Preview97.6%
- Models scored
- 3