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 ...

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 New secret math benchmark stumps AI models and PhDs alike FrontierMath's difficult questions remain unpublished so that AI companies can't train against it.

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.

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 ...

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 ...

Mistral’s second model launch is Mathstral 7B, an AI model designed specifically for math-related reasoning and scientific discovery. Mistral developed Mathstral with Project Numina.

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

'Teachers of Alabama' Alabama school sees math, reading scores soar with new coaching model Published: Oct. 23, 2024, 7:10 a.m.

While the number of ED1 projects is poised to accelerate this year, a growing number of developers and advocates question the math behind it. Soon after assuming office, L.A. Mayor Karen Bass ...

Overview: Free datasets are essential for practice, research, and AI model development.Platforms like Kaggle, UCI, and Google Dataset Search remain top choices ...