A researcher says the plateau is far out with enough scaffolding

Claim

OpenAI's Noam Brown noted the plateau is actually really far out these days, with a well-scaffolded GPT-5.5 able to think for weeks before benchmarks flatten, while Nous Research exposed mixture-of-agent presets as virtual models claiming to beat Opus 4.8 by 8% and GPT-5.5 by 11%.

Reported metric: +8% / +11%

Reporting date: 2026-06-28 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

• Welcome to June 28, 2026 (theinnermostloop.substack.com)