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

Think your basic math skills are still in good shape? There's only one way to find out. 🔢This quiz covers the kind of math ...

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

"Current automated techniques can produce plausible but unreliable (or even incorrect) arguments which are difficult to ...

The result is correct but challenges core norms of mathematics: checking proofs, crediting ideas and keeping research open to ...