The second batch of “First Proof” problems is meant to evaluate AI’s usefulness for research-level math. The best model got ...

A new benchmark pitting AI against previously unseen maths problems shows systems still fall short of top human expertise.

Every year, thousands of college students from across the U.S. and Canada give up a full Saturday before finals begin to take a notoriously difficult, 6-hour math test — and not for a grade, but for ...

The math world is losing its mind over the new solution to an Erdős problem. This is what AI found, how we missed it—and why it matters.

The bat-and-ball problem is a famous math puzzle that more than half of people—even Harvard graduates—get wrong. It's ...

Get out your timer and number two pencil to see if your arithmetic skills from grade school are still intact.

From writing essays to coding, there’s seemingly nothing modern AI chatbots like ChatGPT and Microsoft Copilot cannot accomplish. But even though they seem limitless on the surface, they’re certainly ...