USAMO 2026

USAMO 2026 is a benchmark for hard reasoning in science, technology, engineering and math. It was built to compare language models on a clearly defined set of tasks under the same grading rules, so scores are directly comparable between models.

USAMO 2026 measures hard reasoning in science, technology, engineering and math. In detail, it checks:

• graduate- and expert-level questions in science and math
• multi-step derivations where each step must be correct
• problems written to defeat memorisation (novel or recent exam problems)
• correct use of formulas, units and logical inference

The score is competition points on the organiser's official scale (e.g. a 42-point olympiad-style test). More points is better.

What is the USAMO 2026 benchmark?

USAMO 2026 is a benchmark for hard reasoning in science, technology, engineering and math. It was built to compare language models on a clearly defined set of tasks under the same grading rules, so scores are directly comparable between models.

What does USAMO 2026 test?

USAMO 2026 mainly measures hard reasoning in science, technology, engineering and math. Concretely, it checks: graduate- and expert-level questions in science and math; multi-step derivations where each step must be correct; problems written to defeat memorisation (novel or recent exam problems).

How is the USAMO 2026 score calculated?

The score is competition points on the organiser's official scale (e.g. a 42-point olympiad-style test). More points is better. The declared maximum score of this benchmark is 42.0.

Where do I get USAMO 2026 data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/usamo-2026/scores) or pull it directly from the Open LLM Radar API with any HTTP client.