The AI arena is free today

Open Superagent
AI OrganizationMaintains 4 benchmarks

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.

    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.

    Models scored
    3

In one line

ETH Zurich SRI Lab maintains IMOProof-Adv (counts toward the LLM Stats Score, 1 model scored), MathArena Apex (counts toward the LLM Stats Score, 11 models scored), USAMO 2026 (counts toward the LLM Stats Score, 3 models scored) and USAMO25 (counts toward the LLM Stats Score, 3 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about ETH Zurich SRI Lab.

What is ETH Zurich SRI Lab?

ETH Zurich Secure, Reliable and Intelligent Systems Lab. Runs MathArena and the USAMO proof evaluations. On LLM Stats it maintains 4 benchmarks, led by MathArena Apex, USAMO 2026 and USAMO25. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which ETH Zurich SRI Lab benchmarks count toward the LLM Stats Score?

MathArena Apex, USAMO 2026, USAMO25 and IMOProof-Adv count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead ETH Zurich SRI Lab's benchmarks?

DeepSeek-V4-Pro-Max leads MathArena Apex at 90.2% (11 models scored), MiniMax M3 leads USAMO 2026 at 36 (3 models scored) and Claude Mythos Preview leads USAMO25 at 97.6% (3 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are ETH Zurich SRI Lab's official benchmark results?

ETH Zurich SRI Lab's official site is https://matharena.ai. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.