Muse Wonder
Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.
- Strongest at
- Reading & documents Top 11% of the past year's models · 3 of 4 benchmarks
- Context window
- 1.05M tokens in · 131.1K out
Capability profile
Scored against 91 models released in the past year. 50 is the average model; further out is better.
No results yet: Science, Computer use
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow dot rests on a single benchmark.
- Coding LiveBench: Coding + Agentic Coding
- Writing EQ-Bench Creative Writing v3, Lech Mazur Writing comparison, LiveBench: Instruction Following
- Reading & documents GDP.pdf (Surge AI), Vision Evals: OCR & extraction (low effort), LiveBench: Language + Data Analysis
- Reasoning Mystery Game Puzzles, LiveBench: Reasoning
- Math OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private, ProofBench, LiveBench: Mathematics
- Visual reasoning Vision Evals (low effort), GDP.pdf (Surge AI)
Epoch benchmark boards
Best result on each board it has run. The tick marks the leader.
1 more boards
Meta's past year
8 release days in the past year, about one every 46 days. The next is expected around Dec 15, 2026. Forecasts ↗
Specifications
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.