MMuse Spark 1.3
muse family · launched 2026-09-02
MultimodalReasoningToolsStructuredMuse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.
What this model supports
Strengths by domain
Every result has a source
Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.
Coding2 results
LiveBench 2.0 · CodingLiveBench90.20 scoreReading 90.2
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceAIHOT · CodingAIHOT63.40 scoreReading 63.4
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceResearch & reasoning2 results
LiveBench 2.0 · ResearchLiveBench89.70 scoreReading 89.7
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceAIHOT · ResearchAIHOT64.80 scoreReading 64.8
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceProfessional work2 results
LiveBench 2.0 · ProfessionalLiveBench68.70 scoreReading 68.7
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 2.0, AIHOT aggregateOpen evidenceAIHOT · ProfessionalAIHOT67.80 scoreReading 67.8
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceKnowledge & instruction2 results
LiveBench 2.0 · KnowledgeLiveBench68.60 scoreReading 68.6
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 2.0, AIHOT aggregateOpen evidenceAIHOT · KnowledgeAIHOT68.30 scoreReading 68.3
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceHuman preference & indices4 results
LiveBenchLiveBench74.76 scoreReading 74.8
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceArena TextLMArena1,490.0 EloReading 73.6
Direct LMArena text leaderboard result.
Open evidenceAA IndexArtificial Analysis69.19 indexReading 68.3
Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidenceAIHOT aggregate leaderboardAIHOT65.40 scoreReading 65.4
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence