Muse Spark 1.3 (max)
MetaProprietary
Descripción
Muse Spark 1.3 is Meta Superintelligence Labs' proprietary multimodal reasoning model for long-running agentic, multi-agent, and coding workflows. It improves on Muse Spark 1.2 in long-horizon collaboration, multitasking, instruction following, tool use, failure recovery, and concise coding execution. It supports a 1,048,576-token context window and is available through Muse Code and the Meta Model API. ZeroEval routes to the lower-cost contributor endpoint, where prompts and outputs may be used to improve Meta's products.
Fecha de lanzamiento
2026-09-02
Parámetros
—
Longitud del contexto
1.0M
Modalidades
audio, image, pdf, text, video
Radar de capacidades
59
general
73
coding
94
reasoning
72
science
70
agents
70
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 1 | 72.0 | LS |
| Ranking de codificación | 9 | 94.0 | AA |
| Ranking general | 6 | 94.0 | AA |
| Ranking multimodal | 40 | 58.0 | LS |
| Ciencia | 9 | 91.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
Job Bench
64.9%Aut.
Agentic IF Index (Internal)
57.8%Aut.
AutomationBench
49.4%Aut.
Code
DeepSWE 1.1
75.4%Aut.
SWE Atlas - Codebase QnA
59.4%Aut.
General
GDPval-AA
1754.00 / 3000Aut.
Long Context
MRCR v2 (8-needle)
98.5%Aut.
MRCR v2 (8-needle, 512K-1M)
98.1%Aut.
Multimodal
OSWorld 2.0
66.9%Aut.
Reasoning
Terminal-Bench 2.1
88.8%Aut.
Search
DeepSearchQA
89.4%Aut.
Índices de evaluación AA
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))93.8
Terminalbench V2 185.8
Lcr(Artificial Analysis)79.0
Coding Index(Artificial Analysis)76.3
Intelligence Index(Artificial Analysis)62.1
Scicode(UIUC + Argonne National Lab (2024))57.3
Tau Banking52.4
Hle(Center for AI Safety + Scale AI (2025))49.1
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Legal100
Finance100
Reasoning100
Agents100
General100
Long Context100
Search90
Multimodal70
Code70
Tool Calling70
Vision70
Productivity60
Precios
Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis
Precio de lectura caché$0.15 / 1M tokens
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
2 proveedores
Más barato: Meta Model APIMás caro: EmpirioLabs AI
ProveedorEntradaSalida
1Meta Model APIMás barato
$0
$0
2EmpirioLabs AI
$1.25
$4.25
Comparar precios entre diferentes proveedores de API para este modelo.