*Note: This is the third [AIMO Progress Prize](https://aimoprize.com/) competition. It builds upon the [first AIMO Progress Prize competition](https://www.kaggle.com/c/ai-mathematical-olympiad-prize), which was won in July 2024 by Project Numina and the [second AIMO Progress Prize competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2), which was won in April 2025 by Nvidia’s NemoSkills team. This third competition features a significantly increased problem difficulty, new submission format, expanded prize pool, industry-leading compute resources for participants, new auxiliary prizes to reward community contributions, and updated rules for using open-source LLMs.*

The ability to reason mathematically is a critical milestone for AI. Mathematical reasoning is the foundation for solving many complex problems, from engineering marvels to intricate financial models. However, current AI capabilities are limited in this area.

The AI Mathematical Olympiad (AIMO) Prize is a $10mn fund to spur the open development of AI models capable of performing as well as top human participants in the International Mathematical Olympiad (IMO).

Recent breakthroughs demonstrate AI achieving human-level results on IMO problems. Closed-source models achieved gold medal performance at the 2025 IMO, demonstrating that frontier AI systems are now capable of solving the world's most challenging high school mathematics problems. Our ["OpenAI x AIMO eval"](https://aimoprize.com/updates/2025-09-05-the-gap-is-shrinking) in March 2025 revealed that commercial models could solve 50/50 AIMO2 public leaderboard problems with sufficient compute—despite the highest Kaggle score being just 34/50. This demonstrates a significant gap between closed-source and open-source models in mathematical reasoning capabilities.

AIMO3 is designed to accelerate open-source progress and close this gap. The competition features 110 problems spanning algebra, combinatorics, geometry, and number theory, ranging from National Olympiad level all the way up to IMO standard—the pinnacle of high school mathematical achievement. All problems are entirely original, created by an international team of problem solvers to ensure zero risk of train-test contamination. They have been carefully designed to be 'AI hard', tested against current open LLMs' capabilities. They require genuine mathematical reasoning to solve, making answer-only testing as robust as possible (see Problem 10 in the Reference Problems PDF for a detailed discussion of this design philosophy).

Every problem is entirely original, ensuring zero risk of data contamination. Using this transparent and fair evaluation framework, the competition will help to strengthen the benchmarks for assessing AI models' mathematical reasoning skills. This latest AIMO Progress Prize competition offers an exciting opportunity to drive innovation in the field of AI for Math, while also fostering healthy competition and supporting open science.

Join us as we work towards a future where AI models’ mathematical reasoning skills are accurately and reliably assessed, driving progress and innovation.