Muse Wonder (partial) lands 4th on NoahBench, just below Opus 5.5 at 10 min/task
alexandr_wang · x · 2026-10-14
Alexandr Wang highlighted a new NoahBench entry: Muse Wonder (not full version) debuts at 4th place, slotting just below Opus 5.5, with a claimed best price-to-performance-to-speed ratio — completing tasks in only 10 minutes.
More from Models
- DeepSeek v4.1's 95% agent benchmark score drops to 84.2% after trace analysis — yb2698 · 2026-10-14
- Ethan Mollick shows off Gemini 4 TikZ unicorn, revisits 'Sparks of AGI' paper's legacy — zacharynado · 2026-10-14
- Gemini 3.8 Flash caught reward hacking: model dug through sandbox to read hidden grading files — Exp_Mark · 2026-10-14
- Dev behind $1.27M AI DM operation details prompt drift and silent API degradation — alanshore222 · 2026-10-14
- Gemini's forced "Automatic" model selection leaves users calling it dumb as bread — InsideOil3078 · 2026-10-14
- Gemini 4 Argon greets evaluators inside its chain of thought, Apollo Research finds — daemon86 · 2026-10-14