AI catches up with humans to score 100% at top maths contest

n n

A perfect result at the world’s most prestigious mathematics contest used to be the preserve of a handful of bright young minds each year, but for the first time, artificial intelligence has also scored full marks.

n

Two Chinese tech companies, Huawei and Xiaohongshu, said their AI models each achieved 100 percent on the questions given to human hopefuls at this month’s International Mathematical Olympiad (IMO).

n

They were the first AI labs to announce their scores, but others from around the world may follow suit in the coming days.

n

“We are delighted with this result, because achieving a perfect score at the IMO is extremely challenging,” Xiaohongshu said in a statement this week.

n

“Previously, no large language model had ever achieved a perfect score under the IMO’s official judging process,” the firm added, referring to the tech that underpins AI tools like chatbots.

n

In 2025, models made by the likes of Google and OpenAI reached gold-level scores for the first time — but could not match the abilities of five human contestants who got 100 percent.

n

– ‘Frontier of AI’ –

n

This year, 666 contestants from different countries took part in Shanghai.

n

Just seven of them achieved full marks, according to the official IMO scoreboard.

n

Participants at the IMO, held in different locations each year, must be aged under 20.

n

Huawei said Wednesday that its AI system “Celia” had shown “comprehensive problem-solving capabilities” across several mathematical fields.

n

Xiaohongshu, known as RedNote in English, said its model “dots-note-3.0” had entered the IMO for the first time this year.

n

Tech firms were only provided with the IMO problems after human contestants had taken the exam, with their submissions required within a specified time limit.

n

“During testing, any form of human intervention was strictly prohibited,” and the AI solutions were submitted to IMO organisers for grading, Xiaohongshu said.

n

AI’s progress has been fast: at the 2024 IMO, Google achieved a silver-medal score, solving four of the six problems over two to three days.

n

Deedy Das, a partner at the US-based investment firm Menlo Ventures, said he had given this year’s IMO questions himself to four cutting-edge AI models.

n

All four — from leading US labs OpenAI and Anthropic, the startup Axiom Math and “Kimi K3” from China’s Moonshot AI — scored 42 points out of 42, he said on LinkedIn.

n

“The frontier of AI has officially moved well past IMO math,” Das wrote.

n n