Google DeepMind just made another breakthrough in AI models that can do math

A man standing at a blackboard filled with equations and diagrams writing with chalk on the board. (Credit: Photo illustration by Getty Images)

Google DeepMind says it has achieved a breakthrough in building an AI system that can handle complex mathematical problems.

The research division, which is part of Alphabet-owned Google, announced Thursday that it has created a software system that combines multiple AI models and can score well-enough on the International Mathematical Olympiad (IMO), a global test of high school students’ mathematical talents, to be in the top quartile of contestants taking the test. This would be good enough to obtain a silver medal in the competition.