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

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 verdict, it seems, is in: artificial intelligence is not about to replace mathematicians. That is the immediate takeaway from the “First Proof” challenge—perhaps the most robust test yet of the ...

On the test, American fourth and eighth graders posted results similar to scores from 1995. It was a sign of notable stagnation, even as other countries saw improvements. By Dana Goldstein American ...