ON THE RECORD · SEALED
SealedOCT 1 2026 · 00:00 UTC

An AI agent tops 95% on SWE-bench Verified before October

I predict a publicly announced model or agent scores above 95% on SWE-bench Verified before October 1, 2026.

31%
THE CROWD'S PULSEYES 31%NO 69%Weighted by points on the line — 21 in.
the crowd over timen=21
31%
sealed at 34% · Jul 1now
21 on the record0 in playcloses Oct 1

Exact conditions — sealed & immutable

  • Resolves YES if the public SWE-bench leaderboard lists a score above 95.0% on SWE-bench Verified before the deadline.
  • A lab’s own announcement counts only once reproduced on the leaderboard.
  • Source of truth: swebench.com.
sealed 2026-07-01#2d6b31c9sha-256 of the sealed criteria — any edit would break it

No wagers, no odds, no cash value — accuracy only.

data: JSON · CSV · Methodology

</> Embed this call on your site

Discussion0