Muse Spark

← AI Models
Meta
2026-04-08
Modality:
Intelligence
52.1
#20/537
Coding
47.5
#22/131
Math
Speed
Pricing
Google Preferred Source

Muse Spark is Meta’s model designed for various creative applications. It features an Intelligence Index of 52.1 and a Coding Index of 47.5, making it suitable for tasks that require moderate cognitive and coding capabilities.

When to Use Muse Spark

✓ Best For

  • Creative writing and content generation.
  • Basic coding assistance.
  • Educational tools for learning programming concepts.

✗ Not Ideal For

  • High-performance coding tasks.
  • Complex mathematical computations.

How Muse Spark Compares

Intelligence Index · Higher is better

AnthropicOpenAIMetaKimi

Benchmark Profile

Coding Index

KwaiKATMiniMaxMetaOpenAIDeepSeek

Intelligence · Coding · Math

Intelligence Coding Math

All Benchmark Scores (10)

BenchmarkScore
Intelligence Index 52.1
Coding Index 47.5
GPQA 884%
HLE 399%
SWE-Bench Verified 77.4%
SciCode 51.5%
IFBench 75.9%
LCR 69.7%
TerminalBench Hard 45.5%
Tau2 91.5%

Data: Artificial Analysis · Updated: April 8, 2026

Frequently Asked Questions (15)

When was Muse Spark released?
Muse Spark was released on April 8, 2026.
Who created Muse Spark?
Muse Spark was created by Meta.
How intelligent is Muse Spark?
Muse Spark scores 52 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 13).
How verbose is Muse Spark?
When evaluated on the Intelligence Index, Muse Spark generated 58M output tokens, which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 23M).
Is Muse Spark a reasoning model?
Yes, Muse Spark is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Muse Spark support?
Muse Spark supports text and image input.
What output modalities does Muse Spark support?
Muse Spark supports text output.
Can Muse Spark process images?
Yes, Muse Spark supports image input and can analyze, describe, and answer questions about images.
Is Muse Spark multimodal?
Yes, Muse Spark is multimodal. It can process text and image input and generate text output.
What is the context window of Muse Spark?
Muse Spark has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Muse Spark open source?
No, Muse Spark is proprietary. The model weights are not publicly available.
How many parameters does Muse Spark have?
Muse Spark is a proprietary model and Meta has not disclosed the model size or parameter count.
How does Muse Spark perform on benchmarks?
Muse Spark achieves a score of 52 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Muse Spark available via API?
Check the providers page for current API availability.
Where can I use Muse Spark?
Visit the providers page to see availability.