OpenGPTEvidence-based model decisions
Start evaluationMy Radar
OFFICIAL MODEL PROFILE

Muse Spark 1.1

Catalog entry documented by the provider, with clearly scoped public ranking signals.

MetaMuse SparkCurrent
Add to data comparison
Official model ID
muse-spark-1.1
Provider
Meta
Catalog status
Current
Catalog reviewed
Jul 28, 2026
Model family

Family-level guidance

The following summary describes the broader model family from official positioning. It is not a measured result for this exact version.

Model family: Muse Spark

Muse Spark

Meta's hosted family for agentic, coding, and multimodal work. Muse Spark 1.1 is the current documented release; Muse Spark remains a separate earlier official release.

Solve problems or codeWork with images or audioEveryday workRead, analyze, or writeUse current information or toolsRead long documents
Catalog verification source ↗

Family strengths

Muse Spark 1.1 is positioned for tool use, coding, and multimodal reasoning. Its public Model API identifier is documented as muse-spark-1.1.

Family limitations

The original Muse Spark has no current public Model API identifier documented, so the site does not present one. Access is hosted and availability can depend on region or preview eligibility.

Verify the exact version before choosing: capabilities, price, context limits, latency, tools, and regional availability can differ by provider access path.

Provider documentation and OpenGPT catalog classification are labeled separately.

Version differences

Compare two catalog model IDs from one model family. Provider IDs, sources and published ranking signals are shown; OpenGPT catalog classification is labeled separately.
Muse Spark 1.1 / Muse Spark
Version differencesMuse Spark 1.1Muse Spark
Official model IDmuse-spark-1.1muse-spark
Directory statusStableStable
OpenGPT catalog roleFlagshipPrevious
Current public ranking signalsUser preference 5 · 1495 · Objective tasks 10 · 76.2 · Cost per success 2 · $0.138User preference 7 · 1488
Provider sourceMeta ↗Meta ↗
Model detailsModel details →Model details →

No verified feature-difference data is available. OpenGPT does not infer speed, price, context length, or quality.

OFFICIAL MODEL PROFILE

Official resources

These links go to the provider. Availability and the selectable version can vary by product, account, region, and endpoint.

OFFICIAL MODEL PROFILE

Published ranking signals

Each row preserves one published metric and source. Scores from different sources are not interchangeable.

3
Ranking angleSource positionPublished valueIndependent sourceOpen source result
User preferenceAvailable for in-site data comparison51495LMArenaText Style Control · Jul 24, 2026Published configuration: Text · Style control · OverallOpen source result ↗
Objective tasks1076.2LiveBenchLiveBench-2026-06-25 · Jul 24, 2026Published configuration: xHigh effortOpen source result ↗
Cost per successful task2$0.138LiveBenchLiveBench-2026-06-25 · Jul 24, 2026Published configuration: High effortOpen source result ↗