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 DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 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 BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Model vendor

Meta

Social media company with AI research

Updated Aug 17, 2026. Data as of 2026-08-17

Website
Models13
Versions14
Open defaults3
CountryUS

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

Meta models

Default-version specifications and scored-version capability values are labeled separately.

13 rows
Columns

Show columns

Sort by
Model
LLMBoard
Coverage
Context
License
Released
ModelMEMuse Spark 1.1MetaLLMBoard88.4Coverage40.0%Context1MLicenseClosed weightsReleasedJul 9, 2026
ModelMEMuse Spark 1.2MetaLLMBoard81.6Coverage20.0%Context1MLicenseClosed weightsReleasedAug 5, 2026
ModelMEMuse SparkMetaLLMBoard73.3Coverage60.0%ContextN/ALicenseClosed weightsReleasedApr 8, 2026
ModelMEMuse Glimmer 30BMetaLLMBoard58.5Coverage100.0%Context131.1KLicenseOpen weightsReleasedAug 10, 2026
ModelMELlama 4 MaverickMetaLLMBoard24.2Coverage80.0%Context1MLicenseClosed weightsReleasedApr 5, 2025
ModelMELlama 3.1 405BMetaLLMBoard23.9Coverage100.0%Context128KLicenseClosed weightsReleasedJul 23, 2024
ModelMELlama 3.3 70BMetaLLMBoard21.4Coverage100.0%Context128KLicenseOpen weightsReleasedDec 6, 2024
ModelMELlama 4 ScoutMetaLLMBoard13.5Coverage80.0%Context10MLicenseClosed weightsReleasedApr 5, 2025
ModelMELlama 3.1 70BMetaLLMBoard12.6Coverage100.0%Context128KLicenseClosed weightsReleasedJul 23, 2024
ModelMELlama 3.2 90BMetaLLMBoard9.9Coverage60.0%Context128KLicenseClosed weightsReleasedSep 25, 2024
ModelMELlama 3.1 8BMetaLLMBoard0.0Coverage100.0%Context128KLicenseOpen weightsReleasedJul 23, 2024
ModelMELlama 3.2 11BMetaLLMBoard0.0Coverage60.0%Context128KLicenseClosed weightsReleasedSep 25, 2024
ModelMELlama 3.2 3BMetaLLMBoard0.0Coverage80.0%Context128KLicenseClosed weightsReleasedSep 25, 2024

Meta capability scores

Each unique model uses its latest scored version.

Meta LLMBoard scores

Meta Highlights

Leading Meta models by score, price and context window.

Top scoreMuse Spark 1.188.4 LLMBoardLowest official inputMuse Spark 1.1$1.3 / 1MLargest contextLlama 4 Scout10M tokens
Open-weight defaults3of 13 models

What is Meta?

Background and model catalog information for Meta.

Social media company with AI research

Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.

Vendor
Meta
Models
13
Versions
14
Country
US
Founded
Not available

Catalog data as of 2026-08-17.

FAQ

Common questions about Meta.

What is Meta's highest-ranked model?

Muse Spark 1.1 currently has the strongest LLMBoard score from this vendor.

How many Meta models are tracked?

The catalog contains 13 independently selectable Meta models and 14 versions.

Does Meta host every listed model API?

Not necessarily. Vendor identifies the model developer; API providers are tracked separately.

Does Meta publish open-weight models?

3 current default versions are marked as open weight.