Saltar al contenido principal
AITier

Muse Spark

MetaProprietary

Descripción

Muse Spark is the first model in the Muse family developed by Meta Superintelligence Labs. It is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration. It features a Contemplating mode that orchestrates multiple agents reasoning in parallel. It demonstrates competitive performance in multimodal perception, reasoning, health, and agentic tasks, with Contemplating mode achieving 58% on Humanity's Last Exam and 38% on FrontierScience Research.

Fecha de lanzamiento
2026-04-08
Parámetros
—
Longitud del contexto
—
Modalidades
—

Radar de capacidades

42
general
58
coding
88
reasoning
66
scienceest.
80
agents
70
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica67
54.0
LS
Ranking de codificación33
79.0
AA
Ranking general19
81.0
AA
Ranking multimodal77
60.0
LS
Razonamiento92
50.0
LS
Ciencia15
84.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

GDPval-AA1164.00 / 3000Aut.
DeepSearchQA74.8%Aut.
Terminal-Bench 2.059.0%Aut.
SWE-Bench Pro52.4%Aut.

Biology

GPQA89.5%Aut.

Code

LiveCodeBench Pro0.80 / 3000Aut.
SWE-Bench Verified77.4%Aut.

Communication

Tau2 Telecom91.5%Aut.

General

MMMU-Pro80.4%Aut.
SimpleVQA0.71 / 100Aut.

Grounding

ScreenSpot Pro84.1%Aut.

Healthcare

MedXpertQA78.4%Aut.
HealthBench Hard42.8%Aut.

Math

Humanity's Last Exam58.4%Aut.

Multimodal

CharXiv-R86.4%Aut.
ZEROBench0.33 / 100Aut.

Physics

IPhO 202582.6%Aut.

Reasoning

ERQA64.7%Aut.
ARC-AGI v242.5%Aut.
FrontierScience Research38.3%Aut.

Índices de evaluación AA

Coding Index
58.6
Intelligence Index
43.1
Tau2
0.9
Gpqa
0.9
Ifbench
0.8
Lcr
0.7
Terminalbench V2 1
0.6
Scicode
0.5
Terminalbench Hard
0.5
Hle
0.4
Tau Banking
0.2

Puntuaciones por categoría LLM Stats

Legal
100
Finance
100
Agents
100
General
100
Reasoning
78
Physics
90
Biology
90
Chemistry
90
Communication
90
Frontend Development
80
Grounding
80
Tool Calling
80
Image To Text
70
Multimodal
70
Search
70
Code
70
Vision
70
Math
60
Spatial Reasoning
60
Healthcare
60

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

Fuentes externas

LLM StatsArtificial Analysis