Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Meta · Active

Muse Spark Open

muse family · launched 2026-10-15

MultimodalReasoningToolsStructuredOpen weights
AITopic score66.2#37 overall

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

Evidence coverage90%4 evaluations · 1 institutions
Context / maximum output1M / 1Mtokens
Cache / input / output$0.15 · $1.25 · $4.25USD per million tokens
Value / freshness61.0 / 100relative value · release freshness
Product profile

What this model supports

Inputtext, image, video
Outputtext
Knowledge cutoff2026-01-04
WeightsOpen weights
Capability profile

Strengths by domain

Coding73.61 public results
Research & reasoning73.71 public results
Professional work39.61 public results
Knowledge & instruction80.31 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding1 results

LiveBench 2.0 · CodingLiveBench73.60 scoreReading 73.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence

Research & reasoning1 results

LiveBench 2.0 · ResearchLiveBench73.70 scoreReading 73.7

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence

Professional work1 results

LiveBench 2.0 · ProfessionalLiveBench39.60 scoreReading 39.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0Open evidence

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench80.30 scoreReading 80.3

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0Open evidence

Human preference & indices2 results

LiveBenchLiveBench55.14 scoreReading 55.1

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence
AA IndexArtificial Analysis55.14 indexReading 28.4

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence
Same builder

More from Meta