MathArena (ETH Zurich): leaderboard
Tests LLMs on recent uncontaminated math olympiad problems (IMO, USAMO, AIME, HMMT, Project Euler, and more). Uses item-response theory. 4 runs per problem with cost tracking.
Source: matharena.ai.
Benchmark results
Results are published separately for each benchmark or evaluation setting.
- MathArena - AIME 2025
- MathArena - AIME 2026
- MathArena - APEX 2025
- MathArena - APEX Shortlist 2025
- MathArena - ARXIV April
- MathArena - ARXIV August
- MathArena - ARXIV February
- MathArena - ARXIV June
- MathArena - ARXIV March
- MathArena - ArXiv Math Dec 2025
- MathArena - ArXiv Math Jan 2026
- MathArena - ARXIV September
- MathArena - ARXIV_FALSE April
- MathArena - ARXIV_FALSE August
- MathArena - ARXIV_FALSE February
- MathArena - ARXIV_FALSE June
- MathArena - ARXIV_FALSE March
- MathArena - ARXIV_FALSE September
- MathArena - ARXIVLEAN June
- MathArena - ARXIVLEAN March
- MathArena - ARXIVLEAN September
- MathArena - BrokenArXiv March (Allow Disproving)
- MathArena - BrokenArXiv March (Iterative Self-Correction)
- MathArena - BRUMO 2025
- MathArena - CMIMC 2025
- MathArena - HMMT Feb 2025
- MathArena - HMMT Feb 2026
- MathArena - HMMT Nov 2025
- MathArena - IMC 2025
- MathArena - IMO 2025
- MathArena - IMProofBench Final Answers
- MathArena - IMProofBench Proofs
- MathArena - Kangaroo 2025 Levels 1-2
- MathArena - Kangaroo 2025 Levels 11-12
- MathArena - Kangaroo 2025 Levels 3-4
- MathArena - Kangaroo 2025 Levels 5-6
- MathArena - Kangaroo 2025 Levels 7-8
- MathArena - Kangaroo 2025 Levels 9-10
- MathArena - Project Euler 943-970
- MathArena - Project Euler 971-984
- MathArena - Project Euler 985-988
- MathArena - Putnam 2025
- MathArena - SMT 2025
- MathArena - USAMO 2025
- MathArena - Usamo 2026
- MathArena Arxiv
- MathArena Arxiv False
Interactive version: theaggregate.ai/benchmark?slug=matharena-eth-zurich · How It Works · Data refreshed daily, snapshot 2026-10-20.