Humans outperformed generative AI models created by Google and OpenAI in a top international mathematics competition, despite the programmes achieving gold-level scores for the first time.
Neither model scored full marks—unlike five young people at the International Mathematical Olympiad (IMO), a prestigious annual competition where participants must be under 20 years old.
Google said Monday that an advanced version of its Gemini chatbot had solved five out of the six maths problems set at the IMO, held in Australia’s Queensland this month.
Humans Hold the Edge
“We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score,” the US tech giant cited IMO president Gregor Dolinar as saying.
“Their solutions were astonishing in many respects. IMO, graders found them to be clear, precise, and most of them easy to follow.”
Around 10 per cent of human contestants won gold-level medals, and five received perfect scores of 42 points.
US ChatGPT maker OpenAI said that its experimental reasoning model had scored a gold-level 35 points on the test.
The result “achieved a longstanding grand challenge in AI” at “the world’s most prestigious math competition”, OpenAI researcher Alexander Wei wrote on social media.
“We evaluated our models on the 2025 IMO problems under the same rules as human contestants,” he said.
“For each problem, three former IMO medallists independently graded the model’s submitted proof.”
Google achieved a silver-medal score at last year’s IMO in the British city of Bath, solving four of the six problems.
That took two to three days of computation — far longer than this year, when its Gemini model solved the problems within the 4.5-hour time limit, it said.
The IMO stated that tech companies had “privately tested closed-source AI models on this year’s problems,” the same ones faced by 641 competing students from 112 countries.
“It is very exciting to see progress in the mathematical capabilities of AI models,” said IMO president Dolinar.
Contest organisers could not verify how much computing power had been used by the AI models or whether there had been human involvement, he cautioned.
