Muse Spark 1.1 (Xhigh)
MetaProprietary
Description
Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic tasks. It improves tool and computer use, coding, and multimodal understanding over Muse Spark, can orchestrate parallel subagents, and actively manages a 1,048,576-token context window. The Meta Model API supports text, image, PDF, and video inputs, up to 131,072 output tokens, structured output, parallel tool calling, and built-in web search with citations.
Release Date
2026-07-09
Parameters
—
Context Length
1.0M
Modalities
image, pdf, text, video
Capability Radar
36
general
69
coding
90
reasoning
70
science
80
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 13 | 65.0 | LS |
| Code Ranking | 44 | 87.0 | AA |
| General Ranking | 125 | 56.0 | AA |
| Math Reasoning | 38 | 87.0 | LB |
| Multimodal Ranking | 34 | 60.0 | LS |
| Reasoning | 21 | 88.0 | LB |
| Science | 18 | 84.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Toolathlon
75.6%SR
Finance Agent v2
57.2%SR
Job Bench
54.7%SR
Code
DeepSWE 1.1
53.0%
Multimodal
OSWorld-Verified
80.8%SR
Reasoning
CharXiv-R
88.4%SR
MCP Atlas
88.1%SR
Terminal-Bench 2.1
80.0%SR
Humanity's Last Exam
62.1%SR
SWE-Bench ProPrinceton NLP (2024)
61.5%SR
Vision
BabyVision
76.3%SR
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))89.8
Terminalbench V2 177.9
Lcr(Artificial Analysis)77.7
Coding Index(Artificial Analysis)71.3
Scicode(UIUC + Argonne National Lab (2024))58.8
Hle(Center for AI Safety + Scale AI (2025))46.2
Intelligence Index(Artificial Analysis)33.7
Tau Banking31.8
Terminalbench V4 06.1
LLM Stats Category Scores
(LLM Stats (zeroeval))Multimodal80
Tool Calling80
Vision80
Reasoning70
General70
Agents70
Code70
Math60
Finance60
Productivity50
Pricing
Input Price$1.25 / 1M tokens
Output Price$4.25 / 1M tokens
Blended Price (3:1)$2 / 1M tokens
Cache Read Price$0.15 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
14 providers
Cheapest: Meta Model APIMost Expensive: AIHubMix
ProviderInputOutput
1Meta Model APICheapest
$0
$0
2MetaPRIMARY
$1.25
$4.25
3NanoGPT
$1.25
$4.25
4Abacus
$1.25
$4.25
5OpenRouter
$1.25
$4.25
6Kilo Gateway
$1.25
$4.25
7Vercel AI Gateway
$1.25
$4.25
8DevPass (LLM Gateway)
$1.25
$4.25
9OrcaRouter
$1.25
$4.25
10Merge Gateway
$1.25
$4.25
11Pioneer
$1.25
$4.25
12EmpirioLabs AI
$1.25
$4.25
13LLM Gateway
$1.25
$4.25
14AIHubMix
$1.375
$4.675
Compare pricing across different API providers for this model.