Muse Spark 1.3 (max)
MetaProprietary
Description
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.
Release Date
2026-09-02
Parameters
—
Context Length
1.0M
Modalities
audio, image, pdf, text, video
Capability Radar
59
general
73
coding
94
reasoning
72
science
70
agents
70
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 1 | 72.0 | LS |
| Code Ranking | 9 | 94.0 | AA |
| General Ranking | 6 | 94.0 | AA |
| Multimodal Ranking | 40 | 58.0 | LS |
| Science | 9 | 91.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Job Bench
64.9%SR
Agentic IF Index (Internal)
57.8%SR
AutomationBench
49.4%SR
Code
DeepSWE 1.1
75.4%SR
SWE Atlas - Codebase QnA
59.4%SR
General
GDPval-AA
1754.00 / 3000SR
Long Context
MRCR v2 (8-needle)
98.5%SR
MRCR v2 (8-needle, 512K-1M)
98.1%SR
Multimodal
OSWorld 2.0
66.9%SR
Reasoning
Terminal-Bench 2.1
88.8%SR
Search
DeepSearchQA
89.4%SR
AA Evaluation Indices
(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
LLM Stats Category Scores
(LLM Stats (zeroeval))Legal100
Finance100
Reasoning100
Agents100
General100
Long Context100
Search90
Multimodal70
Code70
Tool Calling70
Vision70
Productivity60
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
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
2 providers
Cheapest: Meta Model APIMost Expensive: EmpirioLabs AI
ProviderInputOutput
1Meta Model APICheapest
$0
$0
2EmpirioLabs AI
$1.25
$4.25
Compare pricing across different API providers for this model.