Revision History
Test-time compute · 13 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected an IMO-ProofBench result that was misattributed to Gemini 2.5 Deep Think and to the wrong source, and fixed a competitive-coding agentic-verifier result that cited an unrelated paper; also repointed several Claude 3.7 Sonnet figures to the right source (plus 18 minor fixes)
Version 13 · Nov 2, 2026, 07:14 AM
- Update: added a video.
Version 12 · Nov 1, 2026, 08:11 AM
- Improve internal links (2026-10-13)
Version 11 · Oct 13, 2026, 10:08 AM
- Correction: the '83%' figure is Mythos Preview's CyberGym vulnerability-reproduction score (83.1% vs 66.6% for Opus 4.6), not a first-attempt working-exploit rate, and it is from Anthropic's Glasswing announcement, not the cited red-team post; linked Project Glasswing
Version 10 · Sep 30, 2026, 07:12 AM
- Added 6 contextual internal links
Version 9 · Jul 23, 2026, 03:05 PM