CLAIM-2026-10-16-02
On SkillForgeBench, Opus 4.8 leads at 40.9% strict completion, and strict completion across the eight agents ranges from 12.6% to 40.9%. The top of that range equals the leader's score by construction, not by coincidence.
Why it matters
Carries a figure or a date used in the 2026-10-16 edition; the sources below are archived in this vault.
Sources
- arxiv2026skillforg