Skip to main content
AITier

Muse Spark

MetaProprietary

Description

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.

Release Date
2026-04-08
Parameters
—
Context Length
—
Modalities
—

Capability Radar

44
general
58
coding
88
reasoning
66
science
80
agents
70
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability128
34.0
LS
Code Ranking67
78.0
AA
General Ranking42
81.0
AA
Multimodal Ranking8
65.0
LS
Science39
84.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

DeepSearchQA74.8%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)59.0%SR
SWE-Bench ProPrinceton NLP (2024)52.4%SR

Biology

GPQANYU + Cohere + Anthropic (2023)89.5%SR

Code

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

Communication

Tau2 Telecom91.5%SR

General

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

Grounding

ScreenSpot Pro84.1%SR

Healthcare

MedXpertQA78.4%SR
HealthBench Hard42.8%SR

Math

Humanity's Last Exam58.4%SR

Multimodal

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

Physics

IPhO 202582.6%SR

Reasoning

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

AA Evaluation Indices

(Artificial Analysis)
Coding Index(Artificial Analysis)
58.6
Intelligence Index(Artificial Analysis)
44.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Lcr(Artificial Analysis)
0.8
Ifbench(Google Research (2023))
0.8
Terminalbench V2 1
0.6
Scicode(UIUC + Argonne National Lab (2024))
0.5
Terminalbench Hard(Stanford × Laude Institute (2026))
0.5
Hle(Center for AI Safety + Scale AI (2025))
0.4

LLM Stats Category Scores

(LLM Stats (zeroeval))
Physics
90
Biology
90
Chemistry
90
Communication
90
Frontend Development
80
Grounding
80
Tool Calling
80
Multimodal
70
Reasoning
70
Search
70
Image To Text
70
General
70
Code
70
Vision
70
Math
60
Spatial Reasoning
60
Healthcare
60
Agents
60
Science
40

Pricing

Input PriceFree
Output PriceFree
Blended Price (3:1)Free

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

No provider data available

External Sources

LLM StatsArtificial Analysis