Muse Wonder (Max)
MetaProprietary
Descripción
Muse Wonder 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 accepts text, images, video, audio, and PDFs and produces text with a 1,048,576-token context window. It is available through the Meta Model API as muse-wonder-1.0 and in Muse Code.
Fecha de lanzamiento
2026-10-12
Parámetros
—
Longitud del contexto
1.0M
Modalidades
audio, image, pdf, text, video
Radar de capacidades
52
general
60
coding
40
reasoning
57
science
50
agents
50
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 105 | 37.0 | LS |
| Ranking de codificación | 32 | 91.0 | AA |
| Ranking general | 8 | 90.0 | AA |
| Ranking multimodal | 141 | 32.0 | LS |
| Ciencia | 18 | 85.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
MemoryBench
85.6%Aut.
JobBench
70.5%Aut.
Personal Superintelligence Index
54.3%Aut.
Program Bench
50.0%Aut.
FocusBench
44.9%Aut.
AutomationBench-AA
39.1%Aut.
Code
DeepSWE 1.1
78.8%Aut.
SWE-Marathon
53.1%Aut.
Terminal-Bench 4.0-AA
52.0%Aut.
Finance
Vals Finance Agent v2
56.6%Aut.
General
Artificial Analysis
52.0%Aut.
GDP.pdf
30.8%Aut.
Healthcare
HealthBench Professional
60.5%Aut.
Knowledge
Harvey LAB-AA
10.0%Aut.
Multimodal
OSWorld 2.1 (partial)
72.6%Aut.
OSWorld 2.1 (strict)
34.3%Aut.
Índices de evaluación AA
(Artificial Analysis)Lcr(Artificial Analysis)80.7
Scicode(UIUC + Argonne National Lab (2024))60.3
Intelligence Index(Artificial Analysis)52.4
Terminalbench V4 052.0
Hle(Center for AI Safety + Scale AI (2025))50.1
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Long Context90
Productivity70
Finance60
Healthcare60
Code60
Knowledge50
Multimodal50
General50
Agents50
Tool Calling50
Vision50
Reasoning40
Precios
Precio de entrada$4 / 1M tokens
Precio de salida$20 / 1M tokens
Precio mixto (3:1)$8 / 1M tokens
Precio de lectura caché$0.2 / 1M tokens
Velocidad
Tokens/seg143.6
Retraso del primer token21.20s
Tiempo hasta la respuesta35.12s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
2 proveedores
Más barato: MetaMás caro: Venice AI
ProveedorEntradaSalida
1MetaPRINCIPAL
$4
$20
2Venice AI
$5
$25
Comparar precios entre diferentes proveedores de API para este modelo.