Top News

For first time, AI scores 100% at International Mathematical Olympiad
23 Jul 2026

In an unprecedented feat, artificial intelligence (AI) has managed to score a perfect 100% at the International Mathematical Olympiad (IMO).

The achievement was announced by Chinese tech giants Huawei and Xiaohongshu, who said their AI systems excelled in the rigorous competition.

This is the first time any large language model has achieved such a result, marking a major milestone in AI development.

AI models scored a perfect score
Performance comparison

Huawei's AI system "Celia" and Xiaohongshu's model "dots-note-3.0" both achieved a perfect score at this year's IMO in Shanghai.

The competition, which took place this July, is known for its extremely difficult problems.

This year, the AI models were only given access to the questions after all human contestants had completed them, ensuring no shortcuts or hints were used.

An LLM aced IMO
AI evolution

The success of Huawei and Xiaohongshu's AI systems at the IMO underscores the rapid progress of artificial intelligence technology. It also raises questions about its potential impact on other fields such as science and engineering.

In 2025, models developed by Google and OpenAI had reached gold-level scores for the first time but couldn't match five human contestants who got a perfect score.

AI models solved all 6 problems
Past results

In 2024, Google's AI model achieved a silver-medal score, solving four out of six problems over two to three days.

This year, Deedy Das from Menlo Ventures tested four cutting-edge AI models with this year's IMO questions. All four models scored a perfect 42/42 points.

"The frontier of AI has officially moved well past IMO math," Das wrote on LinkedIn.