Muse Wonder Full (Max)
MetaProprietary
Descripción
Muse Wonder Full is a proprietary reasoning model from Meta Superintelligence Labs, released on October 12, 2026 for personal and professional agents and long-running coding tasks. Active Memory retains relevant context across interactions, and Active Focus supports sustained task execution and error recovery. Muse Wonder Full is the higher-capability variant, available to Muse Code Power Usage and Maximum Usage subscribers. It is not available through the Meta Model API. The model card specifies text, image, video, and audio inputs, text output, and a 1M-token inference context for both variants.
Fecha de lanzamiento
2026-10-12
Parámetros
—
Longitud del contexto
—
Modalidades
—
Radar de capacidades
55
general
63
coding
50
reasoning
59
science
50
agents
50
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 29 | 58.0 | LS |
| Ranking de codificación | 15 | 94.0 | AA |
| Ranking general | 3 | 97.0 | AA |
| Ranking multimodal | 62 | 55.0 | LS |
| Ciencia | 7 | 90.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
MemoryBench
85.5%Aut.
JobBench
75.3%Aut.
Personal Superintelligence Index
59.1%Aut.
Program Bench
59.0%Aut.
FocusBench
54.2%Aut.
AutomationBench-AA
45.4%Aut.
Code
DeepSWE 1.1
79.0%Aut.
SWE-Marathon
57.5%Aut.
Terminal-Bench 4.0-AA
57.1%Aut.
Finance
Vals Finance Agent v2
59.1%Aut.
General
Artificial Analysis
56.0%Aut.
GDP.pdf
33.2%Aut.
Healthcare
HealthBench Professional
62.3%Aut.
Knowledge
Harvey LAB-AA
13.1%Aut.
Multimodal
OSWorld 2.1 (partial)
78.4%Aut.
OSWorld 2.1 (strict)
39.4%Aut.
Índices de evaluación AA
(Artificial Analysis)Lcr(Artificial Analysis)83.7
Scicode(UIUC + Argonne National Lab (2024))62.6
Terminalbench V4 057.1
Intelligence Index(Artificial Analysis)55.8
Hle(Center for AI Safety + Scale AI (2025))53.6
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Long Context90
Productivity80
Finance60
General60
Healthcare60
Agents60
Code60
Knowledge50
Multimodal50
Reasoning50
Tool Calling50
Vision50
Precios
Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
No hay datos de proveedores disponibles