llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Meta model product

Muse Spark

Muse Spark is a natively multimodal reasoning model developed by Meta Superintelligence Labs.

Updated Oct 23, 2026. Default version: Muse Spark

LLMBoard Score71.2Muse Spark
Coverage80%18 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Muse Spark Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Muse Spark LLMBoard score breakdown

Muse Spark Benchmark Results

Benchmark scores for Muse Spark.

30 of 32 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkFrontierScience ResearchScore38.30%Rank01Participants5Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkHealthBench HardScore42.80%Rank01Participants11Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkIPhO 2025Score82.60%Rank01Participants2Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkMedXpertQAScore78.40%Rank01Participants12Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkLiveCodeBench ProScore0.80 pointsRank05Participants5Percentile0.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkScreenSpot ProScore84.10%Rank05Participants26Percentile84.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkSimpleVQAScore0.71 pointsRank06Participants17Percentile68.75%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena Vision Style ControlScore1,294.09 ratingRank06Participants113Percentile95.54%EvidenceAEvaluatedOct 19, 2026
BenchmarkZEROBenchScore0.33 pointsRank07Participants15Percentile57.14%EvidenceCEvaluatedOct 22, 2026
BenchmarkHumanity's Last ExamScore58.40%Rank08Participants109Percentile93.52%EvidenceCEvaluatedOct 22, 2026
BenchmarkARC-AGI v2Score42.50%Rank10Participants19Percentile50.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkDeepSearchQAScore74.80%Rank11Participants13Percentile16.67%EvidenceCEvaluatedOct 22, 2026
BenchmarkERQAScore64.70%Rank11Participants28Percentile62.96%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena Text Style ControlScore1,489.03 ratingRank12Participants218Percentile94.93%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena VisionScore1,305.77 ratingRank12Participants113Percentile90.18%EvidenceAEvaluatedOct 19, 2026
BenchmarkCharXiv-RScore86.40%Rank14Participants60Percentile77.97%EvidenceCEvaluatedOct 22, 2026
BenchmarkMMMU-ProScore80.40%Rank14Participants73Percentile81.94%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena Document Style ControlScore1,467.29 ratingRank16Participants38Percentile59.46%EvidenceAEvaluatedSep 13, 2026
BenchmarkAA IFBenchScore75.92%Rank16Participants168Percentile91.02%EvidenceBEvaluatedN/A
BenchmarkTau2 TelecomScore91.50%Rank17Participants37Percentile55.56%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA Omniscience AccuracyScore49.60%Rank18Participants201Percentile91.50%EvidenceBEvaluatedN/A
BenchmarkLM Arena TextScore1,474.08 ratingRank21Participants218Percentile90.78%EvidenceAEvaluatedOct 20, 2026
BenchmarkTerminal-Bench 2.0Score59.00%Rank24Participants53Percentile55.77%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena DocumentScore1,444.19 ratingRank24Participants38Percentile37.84%EvidenceAEvaluatedSep 13, 2026
BenchmarkLM Arena Text FactualityScore1,467.64 ratingRank26Participants131Percentile80.77%EvidenceAEvaluatedOct 20, 2026
BenchmarkAA HLE Text No ToolsScore40.69%Rank28Participants200Percentile86.43%EvidenceBEvaluatedN/A
BenchmarkSWE-Bench VerifiedScore77.40%Rank30Participants120Percentile75.63%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA CritPtScore11.33%Rank31Participants200Percentile84.92%EvidenceBEvaluatedN/A
BenchmarkGPQAScore89.50%Rank34Participants256Percentile87.06%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA LCR v1.1Score78.00%Rank45Participants193Percentile77.08%EvidenceBEvaluatedN/A

Muse Spark Arena Results

Preference and agent-evaluation results for the default version.

30 of 89 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenavisionCategoryhumorRank01Rating / score1,343.56Votes237ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryhumorRank02Rating / score1,323.21Votes237ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategoryfrenchRank03Rating / score1,520.23Votes479ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategorygermanRank03Rating / score1,511.24Votes237ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategorycreative writing visionRank04Rating / score1,303.40Votes346ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorycreative writing visionRank05Rating / score1,326.99Votes346ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryenglishRank06Rating / score1,290.07Votes2,428ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryoverallRank06Rating / score1,294.09Votes5,865ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategorykoreanRank07Rating / score1,473.79Votes251ObservationsN/AResult dateOct 20, 2026
ArenatextCategorygermanRank08Rating / score1,497.48Votes237ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryenglishRank09Rating / score1,496.34Votes6,688ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry business and management and financial operationsRank10Rating / score1,489.63Votes2,864ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry legal and governmentRank11Rating / score1,499.91Votes1,017ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryenglishRank11Rating / score1,304.08Votes2,428ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategoryoverallRank12Rating / score1,489.03Votes14,153ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryoverallRank12Rating / score1,305.77Votes5,865ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryocrRank12Rating / score1,302.39Votes4,223ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryfrenchRank13Rating / score1,495.98Votes479ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryexclude tiesRank13Rating / score1,502.15Votes10,728ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategorymulti turnRank13Rating / score1,493.31Votes2,280ObservationsN/AResult dateOct 20, 2026
ArenatextCategorykoreanRank14Rating / score1,458.90Votes251ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryspanishRank14Rating / score1,479.72Votes520ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry entertainment and sports and mediaRank15Rating / score1,461.65Votes2,639ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry software and it servicesRank15Rating / score1,522.50Votes5,557ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategorynon englishRank15Rating / score1,477.43Votes7,465ObservationsN/AResult dateOct 20, 2026
Arenadocument style controlCategoryoverallRank16Rating / score1,467.29Votes1,084ObservationsN/AResult dateSep 13, 2026
Arenatext style controlCategorypolishRank16Rating / score1,485.67Votes312ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryocrRank16Rating / score1,306.58Votes4,223ObservationsN/AResult dateOct 19, 2026
ArenatextCategorypolishRank17Rating / score1,474.51Votes312ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryhard promptsRank17Rating / score1,505.85Votes9,159ObservationsN/AResult dateOct 20, 2026

Muse Spark Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Muse Spark Runtime Performance

Provider-specific output speed and catalog latency for Muse Spark. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Muse Spark Specifications

Technical details for the model's default version.

Version
Muse Spark
Released
Apr 8, 2026
Knowledge cutoff
Unknown
Parameters
N/A
Context window
N/A
Max output
N/A
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Muse Spark Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionMuse SparkReleasedApr 8, 2026LLMBoard71.20ParametersN/AContextN/AMax outputN/AOpen weightsNoLicenseProprietary

Models similar to Muse Spark

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#46+3.66
ME

Muse Spark Open

Meta

74.86 LLMBoard

Details
#39+5.00
ME

Muse Spark 1.2

Meta

76.20 LLMBoard

Details
#35+6.76
ME

Muse Wonder

Meta

77.96 LLMBoard

Details
#21+11.41
ME

Muse Spark 1.1

Meta

82.61 LLMBoard

Details
#15+12.26
ME

Muse Wonder Full

Meta

83.46 LLMBoard

Details
#103-13.39
ME

Muse Glimmer 30B

Meta

57.81 LLMBoard

Details

What is Muse Spark?

Key information about Muse Spark and its available data.

Muse Spark is the first model in the Muse family, with support for tool-use, visual chain of thought, and multi-agent orchestration. Its Contemplating mode orchestrates multiple agents reasoning in parallel and achieved 58% on Humanity's Last Exam and 38% on FrontierScience Research.

Data as of 2026-10-22.

FAQ

Common questions about Muse Spark.

When was Muse Spark released?

Muse Spark's default version was released on Apr 8, 2026.

How much does Muse Spark cost?

No official standard PAYG price is currently available for Muse Spark.

Who created Muse Spark?

Muse Spark was created by Meta.

What is the context window for Muse Spark?

A context window is not available for the default version.

Is Muse Spark open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Muse Spark?

No provider offering is currently linked to the default version.

Browse runtime rankings