Muse Spark Open: Intelligence, Performance & Price Analysis
Available providers
Model summary
Muse Spark Open (Xhigh) is above average in intelligence, but particularly expensive when comparing to other open weight models of similar size. It's also notably quick per task and fairly concise. The model supports text, image, speech, and video input, outputs text, and has a 1M tokens context window.
Muse Spark Open (Xhigh) scores 25 on the Artificial Analysis Intelligence Index, placing it above average among comparable models (median: 23). When evaluating the Intelligence Index, it generated 90.6M tokens, which is fairly concise in comparison to the median of 104M.
Pricing for Muse Spark Open (Xhigh) is $1.25 per 1M input tokens (expensive, median: $0.43) and $4.25 per 1M output tokens (expensive, median: $1.84). On average, it costs $2.02 per task to evaluate Muse Spark Open (Xhigh) on the Intelligence Index.
At 6.0 minutes per Intelligence Index task, Muse Spark Open (Xhigh) is notably quick compared with the median of 13.7 minutes for comparable models (lower is better).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text, image, speech, and video |
| Output modality | Supports: text |
| Context window | 1M ~1573 A4 pages of size 12 Arial font |
| Total parameters | 816B |
| Active parameters | 42B Number of parameters active per token during inference |
| License | Muse Model License |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Capability Indexes
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Agentic real-world work tasks, Elo
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
AA-PersonalityBench
Personality Indexes
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Token Use
Output Tokens per Intelligence Index Task
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Muse Spark Open (Xhigh) | 25 | 816B 42B active at inference time | 1M | $0.78 | 6.0 | 185 | +2 |
Frequently Asked Questions
Common questions about Muse Spark Open
Muse Spark Open was released on October 15, 2026.
Muse Spark Open was created by Meta.
Muse Spark Open scores 25 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 23).
Muse Spark Open takes 6.0 minutes per Intelligence Index task (based on the median across providers serving the model), which is among the quickest compared to other open weight models of similar size (median: 13.7 minutes; lower is better).
Muse Spark Open has a time to first answer token of 10.18s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 19.92s).
Muse Spark Open costs $1.25 per 1M input tokens (at the higher end, median: $0.43) and $4.25 per 1M output tokens (at the higher end, median: $1.84), based on the median across providers serving the model.
Muse Spark Open costs $1.25 per 1M input tokens and $4.25 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.78 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Muse Spark Open generated 90.6M output tokens, which is better than average compared to other open weight models of similar size (median: 104M).
Yes, Muse Spark Open is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Muse Spark Open supports text, image, speech, and video input.
Muse Spark Open supports text output.
Yes, Muse Spark Open supports image input and can analyze, describe, and answer questions about images.
Yes, Muse Spark Open is multimodal. It can process text, image, speech, and video input and generate text output.
Muse Spark Open has a context window of 1M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Muse Spark Open is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Muse Spark Open has 816B parameters (42B active).
Muse Spark Open is a Mixture of Experts (MoE) model with 816B total parameters, but only 42B active parameters are used during inference.
Muse Spark Open is released under the Muse Model License license. Commercial use is allowed with restrictions. View license
Muse Spark Open achieves a score of 25 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across knowledge work, coding, science, and general knowledge.
Yes, Muse Spark Open is available via API through 5 providers. Compare API providers
Muse Spark Open is available through 5 API providers. Compare providers