Atlas

Benchmarks

← All benchmarks

FrontierMath Erdős

Math · 2026-09-03

68 formal conjectures covering 65 difficult Erdős problems open as of August 2026. An Inspect DeepAgent with offline mathematics literature attempts a Lean proof or disproof once per conjecture, within $300 and 72 hours. Comparator verifies submitted proofs in an isolated container.

Top models (higher is better)

ModelScore
GPT-6 Astra2.9
Claude Fable 5.10.0
Claude Fable 50.0
GPT-5.50.0
GPT-5.6 Sol0.0
Loading Atlas data…