GPT 5.6 Breakthrough on Large Prime Gaps Verified in Lean

cloneofsimo · x · 2026-08-30

Reports indicate GPT 5.6 achieved a stronger result on large prime gaps, improving upon the best bound by Ford-Green-Konyagin-Maynard-Tao [2014] by a factor of log3 X / (log4 X)^2. Terence Tao had previously noted that breaking his result would require genuinely new ideas. The result has also reportedly been verified unconditionally in Lean.

Related event: GPT 5.6 Improves Long-Standing Prime Gap Bound(3 posts)→

Original post →

More from Research

Research channel →