A few months before the 2025 International Mathematical Olympiad (IMO) in July, a three-person team at OpenAI made a long bet ...

OpenAI researchers reveal how their experimental model, devoid of any external aids, powered through hours-long proofs to earn a gold-medal score at the International Math Olympiad—and they discuss th ...

And yet, recently, Gemini 2.5 Pro and OpenAI’s o3 scored 86.7% and 88.9%, respectively, in the American Invitational Mathematics Examination, a key math benchmark for AI models.

secret math problems dept. New secret math benchmark stumps AI models and PhDs alike FrontierMath's difficult questions remain unpublished so that AI companies can't train against it.

To measure the problem-solving ability of large and general-purpose language models, the researchers created a dataset called MATH, which consists of 12,500 problems taken from high school math ...

A University of Queensland researcher has developed a new mathematical model to explain the evolution of the universe which, ...

Microsoft enhances the capabilities of small language models (SLMs) with rStar-Math. The technique boosts the capabilities of SLMs, allowing them to compete or even surpass the math reasoning ...

Chinese AI lab DeepSeek has quietly updated Prover, its AI system that's designed to solve math-related proofs and theorems.

The reason for this is fundamental: ChatGPT, and many models like it, can't actually do math. They rely on sophisticated pattern recognition and statistical memory, not true mathematical computation.

While the number of ED1 projects is poised to accelerate this year, a growing number of developers and advocates question the math behind it.