FutureSim Q3 eval: Opus 5.5 dethrones GPT, spawns 50+ subagents in 90-day simulation
maksym_andr · x · 2026-11-16
New FutureSim Q3 simulation results show Opus 5.5 overtaking GPT at the top, with strong priors and impressive test-time adaptation.
- Opus 5.5 called 50+ subagents and produced over 400 research notes during the 90-day simulation
- It was 50% more token-efficient than 6.1 Sol
- maksymandr notes Opus 5.5 is clearly ahead of the rest
More from Models
- Percy Liang to AI labs: share non-vacuous info outsiders can actually evaluate — lateinteraction · 2026-11-16
- Anthropic model personality watch: Mythos 5 'inhabits the god frame,' 5.1 doesn't — repligate · 2026-11-16
- Dev: intent-gap between Sol-6.1 and Opus 5.5 is huge, suspects distillation — sytelus · 2026-11-16
- 'Sonnet at home' debunked: Qwen 27B and Gemma 31B fail a trivial bash one-shot that GPT-4.1 Nano passes — dtdisapointingresult · 2026-11-16
- Users report GPT-6.1-high requests silently routed to PT-6.2-high, seek opt-out — Striking-Loan-1118 · 2026-11-16
- Dev rates model personalities: Claude cautious, Grok great at search, DeepSeek persistent, Qwen smart but untrusted — gnukeith · 2026-11-16