IMO 2025

IMO 2025 evaluates on the problems of the International Mathematical Olympiad 2025. The score follows the official 42-point olympiad scale, in which each of the six problems is graded by human- or model-judged criteria. It shows whether a model can produce real olympiad-level proofs.

IMO 2025 measures hard reasoning in science, technology, engineering and math. In detail, it checks:

• full mathematical proofs, not just final answers
• the olympiad grading scale (42 points maximum)
• creativity in finding solution routes
• correct, rigorous reasoning over many steps

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 IMO 2025 benchmark?

IMO 2025 evaluates on the problems of the International Mathematical Olympiad 2025. The score follows the official 42-point olympiad scale, in which each of the six problems is graded by human- or model-judged criteria. It shows whether a model can produce real olympiad-level proofs.

What does IMO 2025 test?

IMO 2025 mainly measures hard reasoning in science, technology, engineering and math. Concretely, it checks: full mathematical proofs, not just final answers; the olympiad grading scale (42 points maximum); creativity in finding solution routes.

How is the IMO 2025 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 IMO 2025 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/imo-2025/scores) or pull it directly from the Open LLM Radar API with any HTTP client.