Muse Spark Open
Built with Muse Spark Open. Meta's open-weight 816B-A42B model for coding and agentic workflows. Text and image input, text output, tool calling and structured output. Always reasons at low, medium, high, or xhigh effort. Custom Muse Model License and Usage Policy apply.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Oct 15, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $1.25
- Output
- $4.25
- Cache read
- $0.15
Specifications
- Context window
- 1M
- Max output
- N/A
- Parameters
- 816B / 42B
- Total / active
- Avg output (7d)
- 1.3K tokens
- Longer than 80% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
38.9
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
49.7%
Better than 66% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
20.9%
Better than 69% of models compared
AA-Briefcase v1.1
Agentic knowledge work (Elo)
1279 Elo
Better than 68% of models compared
GDPval-AA v2.1
Economically valuable tasks (Elo)
1401 Elo
Better than 75% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
18.6%
Better than 68% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
78.3%
Better than 80% of models compared
Reasoning
HLE
Humanity's Last Exam
43.9%
Better than 92% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
8.1%
Better than 58% of models compared
SciCode
Python programming for scientific computing
58.4%
Better than 90% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
89.0%
Better than 86% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
78.3%
Better than 80% of models compared
Last updated Oct 22, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…