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
1224 models729 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 1.3

3 is Meta Superintelligence Labs' proprietary multimodal reasoning model for long-running agentic, multi-agent, and coding workflows.

Updated Sep 8, 2026. Default version: Muse Spark 1.3

LLMBoard Score90.8Muse Spark 1.3
Coverage0%10 benchmark families
Context window1MTokens
Official input price$1.25Meta API

On this page

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

Muse Spark 1.3 Capability Profile

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

Muse Spark 1.3 LLMBoard score breakdown

Muse Spark 1.3 Benchmark Results

Benchmark scores for Muse Spark 1.3.

12 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkAgentic IF Index (Internal)Score57.80%Rank01Participants1Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkAutomationBenchScore49.40%Rank01Participants18Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkDeepSWE 1.1Score75.40%Rank01Participants31Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkJob BenchScore64.90%Rank01Participants8Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkMRCR v2 (8-needle)Score98.50%Rank01Participants24Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkMRCR v2 (8-needle, 512K-1M)Score98.10%Rank01Participants4Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkSWE Atlas - Codebase QnAScore59.40%Rank01Participants3Percentile100.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkTerminal-Bench 2.1Score88.80%Rank03Participants35Percentile94.12%EvidenceCEvaluatedSep 8, 2026
BenchmarkGDPval-AAScore1,754.00 pointsRank04Participants9Percentile62.50%EvidenceCEvaluatedSep 8, 2026
BenchmarkOSWorld 2.0Score66.90%Rank04Participants11Percentile70.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkDeepSearchQAScore89.40%Rank05Participants10Percentile55.56%EvidenceCEvaluatedSep 8, 2026
BenchmarkLM Arena WebdevScore1,622.48 ratingRank09Participants97Percentile91.67%EvidenceAEvaluatedSep 5, 2026

Muse Spark 1.3 Arena Results

Preference and agent-evaluation results for the default version.

4 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenawebdevCategorywebdev-htmlRank06Rating / score1,655.81Votes107ObservationsN/AResult dateSep 5, 2026
ArenawebdevCategoryoverallRank09Rating / score1,622.48Votes1,274ObservationsN/AResult dateSep 5, 2026
ArenawebdevCategorywebdevRank09Rating / score1,622.48Votes1,274ObservationsN/AResult dateSep 5, 2026
ArenawebdevCategorywebdev-reactRank11Rating / score1,626.67Votes882ObservationsN/AResult dateSep 5, 2026

Muse Spark 1.3 Pricing

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

Official API
$1.25 input, $4.25 output per 1M
Official provider
Meta
Lowest third-party
From $1.25 input, $4.25 output per 1M via NanoGPT
Tracked offerings
9
9 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderNanoGPTProvider model IDmeta/muse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderOpenRouterProvider model IDmeta/muse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderVercel AI GatewayProvider model IDmeta/muse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderKilo GatewayProvider model IDmeta/muse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderMetaProvider model IDmuse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderLLM GatewayProvider model IDmeta/muse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderEmpirioLabs AIProvider model IDmuse-spark-1-3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderDevPass (LLM Gateway)Provider model IDmuse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026
ProviderOpenCode ZenProvider model IDmuse-spark-1.3RegionglobalInput / 1M$1.25Output / 1M$4.25Context1MUpdatedSep 8, 2026

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

Muse Spark 1.3 Runtime Performance

Provider-specific output speed and catalog latency for Muse Spark 1.3. Runtime does not affect the capability score.

1 row
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderMeta Model APIOutput Speed8.44 tok/sCatalog Latency7.91 sMax Input1MMax Output943.7KUpdatedSep 8, 2026

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

Muse Spark 1.3 Specifications

Technical details for the model's default version.

Version
Muse Spark 1.3
Released
Sep 2, 2026
Knowledge cutoff
Unknown
Parameters
N/A
Context window
1M
Max output
943.7K
Inputs
audio, image, text, video
Outputs
text
Open weights
No
License
Proprietary

Muse Spark 1.3 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 Spark 1.3ReleasedSep 2, 2026LLMBoard90.82ParametersN/AContext1MMax output943.7KOpen weightsNoLicenseProprietary

Models similar to Muse Spark 1.3

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

#14-5.65
ME

Muse Spark 1.1

Meta

85.17 LLMBoard

Details
#24-11.84
ME

Muse Spark 1.2

Meta

78.98 LLMBoard

Details
#40-18.73
ME

Muse Spark

Meta

72.09 LLMBoard

Details
#79-33.43
ME

Muse Glimmer 30B

Meta

57.39 LLMBoard

Details
#200-67.38
ME

Llama 4 Maverick

Meta

23.44 LLMBoard

Details
#203-67.94
ME

Llama 3.1 405B

Meta

22.88 LLMBoard

Details

What is Muse Spark 1.3?

Key information about Muse Spark 1.3 and its available data.

2 in long-horizon collaboration, multitasking, instruction following, tool use, failure recovery, and concise coding execution. It supports a 1,048,576-token context window and is available through Muse Code and the Meta Model API.

Data as of 2026-09-08.

FAQ

Common questions about Muse Spark 1.3.

When was Muse Spark 1.3 released?

Muse Spark 1.3's default version was released on Sep 2, 2026.

How much does Muse Spark 1.3 cost?

Muse Spark 1.3's official API price is $1.25 per million input tokens and $4.25 per million output tokens via Meta. The lowest tracked third-party offer starts at $1.25 input and $4.25 output via NanoGPT.

Who created Muse Spark 1.3?

Muse Spark 1.3 was created by Meta.

What is the context window for Muse Spark 1.3?

The default version has a 1M token context window.

Is Muse Spark 1.3 open weight?

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

How many API providers offer Muse Spark 1.3?

9 provider offerings are linked to the default version.