Testing AIs on 68 of the hardest open Erdos problems, verified in Lean

Testing AIs on 68 of the hardest open Erdos problems, verified in Lean arxiv.org

We introduce FrontierMath Erdős (FME), a benchmark of 68 Erdős problems that are open as of August 2026. To solve a task in FME, AI systems must resolve (prove or disprove) one of the 68 conjectures in the proof…

3 points•tadamcz•8 days ago•0 comments•

#testing #verified #lean #ais #hardest #erdos #testing ais #hardest open

0 comments

No comments yet.

0 comments

Related stories