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
1450 models809 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

Llama 3.1 8B

1 8B is a multilingual large language model optimized for dialogue use cases.

Updated Nov 18, 2026. Default version: Llama 3.1 8B Instruct

LLMBoard Score0.0Llama 3.1 8B Instruct
Coverage20%16 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Llama 3.1 8B Capability Profile

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

Llama 3.1 8B Instruct LLMBoard score breakdown

Llama 3.1 8B Benchmark Results

Benchmark scores for Llama 3.1 8B Instruct.

20 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMBPP EvalPlus (base)Score72.80%Rank01Participants1Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkGSM-8K (CoT)Score84.50%Rank02Participants2Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkAPI-BankScore82.60%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkBFCLScore76.10%Rank03Participants11Percentile80.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkGorilla Benchmark API BenchScore8.20%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMLU (CoT)Score73.00%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMultilingual MGSM (CoT)Score68.90%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMultipl-E HumanEvalScore50.80%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMultipl-E MBPPScore52.40%Rank03Participants3Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkNexusScore38.50%Rank03Participants4Percentile33.33%EvidenceCEvaluatedNov 17, 2026
BenchmarkMATH (CoT)Score51.90%Rank06Participants6Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkARC-CScore83.40%Rank16Participants35Percentile55.88%EvidenceCEvaluatedNov 17, 2026
BenchmarkDROPScore59.50%Rank24Participants30Percentile20.69%EvidenceCEvaluatedNov 17, 2026
BenchmarkHumanEvalScore72.60%Rank54Participants66Percentile18.46%EvidenceCEvaluatedNov 17, 2026
BenchmarkIFEvalScore80.40%Rank57Participants71Percentile20.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMLUScore69.40%Rank88Participants104Percentile15.53%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMLU-ProScore48.30%Rank128Participants142Percentile9.93%EvidenceCEvaluatedNov 17, 2026
BenchmarkLM Arena TextScore1,186.62 ratingRank214Participants221Percentile3.18%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena Text Style ControlScore1,211.30 ratingRank218Participants221Percentile1.36%EvidenceAEvaluatedNov 11, 2026
BenchmarkGPQAScore30.40%Rank254Participants265Percentile4.17%EvidenceCEvaluatedNov 17, 2026

Llama 3.1 8B Arena Results

Preference and agent-evaluation results for the default version.

30 of 56 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenatextCategoryjapaneseRank182Rating / score1,061.20Votes1,234ObservationsN/AResult dateNov 11, 2026
ArenatextCategorykoreanRank182Rating / score1,052.93Votes802ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryfrenchRank183Rating / score1,177.27Votes478ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryspanishRank184Rating / score1,169.10Votes565ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryjapaneseRank184Rating / score1,086.88Votes1,234ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorykoreanRank184Rating / score1,086.50Votes802ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryfrenchRank186Rating / score1,206.60Votes478ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryspanishRank189Rating / score1,188.72Votes565ObservationsN/AResult dateNov 11, 2026
ArenatextCategorygermanRank192Rating / score1,144.12Votes1,295ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorygermanRank194Rating / score1,167.76Votes1,295ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry medicine and healthcareRank207Rating / score1,181.59Votes2,564ObservationsN/AResult dateNov 11, 2026
ArenatextCategorymathRank207Rating / score1,179.24Votes7,135ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry legal and governmentRank208Rating / score1,206.25Votes2,882ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry mathematicalRank208Rating / score1,180.36Votes5,985ObservationsN/AResult dateNov 11, 2026
ArenatextCategorychineseRank209Rating / score1,150.89Votes4,400ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry software and it servicesRank209Rating / score1,194.90Votes13,139ObservationsN/AResult dateNov 11, 2026
ArenatextCategorycodingRank210Rating / score1,194.68Votes8,582ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryhard prompts englishRank210Rating / score1,195.54Votes8,195ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry business and management and financial operationsRank210Rating / score1,165.82Votes5,722ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryenglishRank211Rating / score1,217.54Votes26,610ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryexpertRank211Rating / score1,143.72Votes2,589ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryhard promptsRank211Rating / score1,174.61Votes13,535ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry life and physical and social scienceRank211Rating / score1,193.33Votes8,403ObservationsN/AResult dateNov 11, 2026
ArenatextCategorymulti turnRank211Rating / score1,171.90Votes8,930ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorymathRank212Rating / score1,188.32Votes7,135ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryinstruction followingRank213Rating / score1,158.81Votes19,781ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorychineseRank213Rating / score1,204.14Votes4,400ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryexclude tiesRank214Rating / score1,055.00Votes31,686ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry entertainment and sports and mediaRank214Rating / score1,144.58Votes7,706ObservationsN/AResult dateNov 11, 2026
ArenatextCategorylonger queryRank214Rating / score1,181.37Votes6,736ObservationsN/AResult dateNov 11, 2026

Llama 3.1 8B Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.02 input, $0.04 output per 1M via NanoGPT
Tracked offerings
14
14 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderNanoGPTProvider model IDmeta-llama/llama-3.1-8b-instructRegionglobalInput / 1M$0.02Output / 1M$0.04Context131.1KUpdatedNov 18, 2026
ProviderOpenRouterProvider model IDmeta-llama/llama-3.1-8b-instructRegionglobalInput / 1M$0.02Output / 1M$0.04Context131.1KUpdatedNov 18, 2026
ProviderHeliconeProvider model IDllama-3.1-8b-instructRegionglobalInput / 1M$0.02Output / 1M$0.05Context16.4KUpdatedNov 18, 2026
ProviderNovita AIProvider model IDmeta-llama/llama-3.1-8b-instructRegionglobalInput / 1M$0.02Output / 1M$0.05Context16.4KUpdatedNov 18, 2026
ProviderKilo GatewayProvider model IDmeta-llama/llama-3.1-8b-instructRegionglobalInput / 1M$0.02Output / 1M$0.04Context131.1KUpdatedNov 18, 2026
ProviderAbacusProvider model IDmeta-llama/Meta-Llama-3.1-8B-InstructRegionglobalInput / 1M$0.02Output / 1M$0.05Context128KUpdatedNov 18, 2026
ProviderInferenceProvider model IDmeta/llama-3.1-8b-instructRegionglobalInput / 1M$0.025Output / 1M$0.025Context16KUpdatedNov 18, 2026
ProviderKitaniProvider model IDmeta-llama/llama-3.1-8b-instructRegionglobalInput / 1M$0.049Output / 1M$0.0765Context8.2KUpdatedNov 18, 2026
ProviderHugging FaceProvider model IDmeta-llama/Llama-3.1-8B-InstructRegionglobalInput / 1M$0.06Output / 1M$0.06Context131.1KUpdatedNov 18, 2026
ProviderNeonProvider model IDmeta-llama-3-1-8b-instructRegionglobalInput / 1M$0.15Output / 1M$0.45Context131.1KUpdatedNov 18, 2026
ProviderZeroGPUProvider model IDllama-3.1-8b-instruct-fastRegionglobalInput / 1M$0.15Output / 1M$0.28Context131.1KUpdatedNov 18, 2026
ProviderAmazon BedrockProvider model IDmeta.llama3-1-8b-instruct-v1:0RegionglobalInput / 1M$0.22Output / 1M$0.22Context128KUpdatedNov 18, 2026
ProviderMerge GatewayProvider model IDmeta/llama-3.1-8b-instructRegionglobalInput / 1M$0.22Output / 1M$0.22Context128KUpdatedNov 18, 2026
ProviderVercel AI GatewayProvider model IDmeta/llama-3.1-8bRegionglobalInput / 1M$0.22Output / 1M$0.22Context128KUpdatedNov 18, 2026

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

Llama 3.1 8B Runtime Performance

Provider-specific output speed and catalog latency for Llama 3.1 8B Instruct. Runtime does not affect the capability score.

3 rows
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderCerebrasOutput Speed2,047.00 tok/sCatalog Latency0.20 sMax Input131.1KMax Output131.1KUpdatedNov 18, 2026
ProviderSambanovaOutput Speed1,050.00 tok/sCatalog Latency0.50 sMax Input131.1KMax Output131.1KUpdatedNov 18, 2026
ProviderGroqOutput Speed750.00 tok/sCatalog Latency0.50 sMax Input131.1KMax Output131.1KUpdatedNov 18, 2026

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

Llama 3.1 8B Specifications

Technical details for the model's default version.

Version
Llama 3.1 8B Instruct
Released
Jul 23, 2024
Knowledge cutoff
Dec 31, 2023
Parameters
8B
Context window
131.1K
Max output
131.1K
Inputs
text
Outputs
text
Open weights
Yes
License
Llama 3.1 Community License

Llama 3.1 8B 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
VersionLlama 3.1 8B InstructReleasedJul 23, 2024LLMBoard0.00Parameters8BContext131.1KMax output131.1KOpen weightsYesLicenseLlama 3.1 Community License

Models similar to Llama 3.1 8B

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

#3400.00
ME

Llama 3.2 11B

Meta

0.00 LLMBoard

Details
#3410.00
ME

Llama 3.2 3B

Meta

0.00 LLMBoard

Details
#305+8.24
ME

Llama 3.2 90B

Meta

8.24 LLMBoard

Details
#299+10.28
ME

Llama 3.1 70B

Meta

10.28 LLMBoard

Details
#297+10.94
ME

Llama 4 Scout

Meta

10.94 LLMBoard

Details
#271+18.95
ME

Llama 3.3 70B

Meta

18.95 LLMBoard

Details

What is Llama 3.1 8B?

Key information about Llama 3.1 8B and its available data.

1 8B Instruct is a multilingual large language model with a 128K context length, tool use, and reasoning capabilities.

Data as of 2026-11-17.

FAQ

Common questions about Llama 3.1 8B.

When was Llama 3.1 8B released?

Llama 3.1 8B's default version was released on Jul 23, 2024.

How much does Llama 3.1 8B cost?

No official standard PAYG price is currently available for Llama 3.1 8B. The lowest tracked third-party offer starts at $0.02 input and $0.04 output via NanoGPT.

Who created Llama 3.1 8B?

Llama 3.1 8B was created by Meta.

What is the context window for Llama 3.1 8B?

The default version has a 131.1K token context window.

Is Llama 3.1 8B open weight?

Yes. The default version is marked as open weight under Llama 3.1 Community License.

How many API providers offer Llama 3.1 8B?

14 provider offerings are linked to the default version.