llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsLlama 3.3 70B

Meta model product

Llama 3.3 70B

Llama 3.3 is a multilingual large language model optimized for dialogue use cases across multiple languages. It is a pretrained and instruction-tuned generative model with 70 billion parameters, outperforming many open-source and closed chat models on common industry benchmarks. Llama 3.3 supports a context length of 128,000 tokens and is designed for commercial and research use in multiple languages.

Updated Aug 10, 2026. Default version: Llama 3.3 70B Instruct

Compare
LLMBoard score54.6Llama 3.3 70B Instruct
Coverage80%6 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Model specification

Structured fields from the published default version.

Version
Llama 3.3 70B Instruct
Released
Dec 6, 2024
Knowledge cutoff
Dec 1, 2023
Parameters
70B
Context window
128K
Max output
4.1K
Inputs
text
Outputs
text
Open weights
Yes
License
Llama 3.3 Community License Agreement

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Llama 3.3 70B Instruct category scores

Benchmark results

Published benchmark records for the scored version Llama 3.3 70B Instruct.

9 rows
Columns

Show columns

BFCL v20.815100.0%CAug 7, 2026
MBPP EvalPlus0.9220.0%CAug 7, 2026
MGSM0.953186.7%CAug 7, 2026
IFEval0.996587.5%CAug 7, 2026
MATH0.8237168.6%CAug 7, 2026
HumanEval0.9247669.3%CAug 7, 2026
MMLU0.93410066.7%CAug 7, 2026
MMLU-Pro0.78712932.8%CAug 7, 2026
GPQA0.517523325.0%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

text style controlpolish1801317.31,428N/AAug 6, 2026
textpolish1931258.01,428N/AAug 6, 2026
textfrench1961278.8535N/AAug 6, 2026
text style controljapanese1981213.31,121N/AAug 6, 2026
textspanish2011266.5590N/AAug 6, 2026
textjapanese2031149.31,121N/AAug 6, 2026
text style controlfrench2031324.3535N/AAug 6, 2026
text style controlgerman2051290.91,182N/AAug 6, 2026
textgerman2061251.21,182N/AAug 6, 2026
text style controlspanish2101300.5590N/AAug 6, 2026
text style controlindustry legal and government2121341.73,173N/AAug 6, 2026
text style controlkorean2161212.7846N/AAug 6, 2026
text style controlindustry medicine and healthcare2181340.52,746N/AAug 6, 2026
text style controlenglish2231344.030,128N/AAug 6, 2026
text style controlindustry life and physical and social science2231340.29,373N/AAug 6, 2026
textkorean2241139.2846N/AAug 6, 2026
text style controlmulti turn2251317.29,135N/AAug 6, 2026
text style controlindustry entertainment and sports and media2281285.59,737N/AAug 6, 2026
textindustry medicine and healthcare2291274.32,746N/AAug 6, 2026
text style controlindustry mathematical2291301.85,231N/AAug 6, 2026
text style controlmath2291296.05,772N/AAug 6, 2026
text style controlcreative writing2301286.18,056N/AAug 6, 2026
textindustry legal and government2311283.93,173N/AAug 6, 2026
textenglish2321304.130,128N/AAug 6, 2026
textmulti turn2321280.79,135N/AAug 6, 2026
text style controloverall2341318.354,698N/AAug 6, 2026
text style controlexclude ties2341262.436,895N/AAug 6, 2026
text style controlexpert2341295.42,893N/AAug 6, 2026
text style controlhard prompts english2341338.110,078N/AAug 6, 2026
textcreative writing2381251.88,056N/AAug 6, 2026
textindustry life and physical and social science2401284.59,373N/AAug 6, 2026
textindustry mathematical2401267.35,231N/AAug 6, 2026
text style controlhard prompts2401320.717,004N/AAug 6, 2026
text style controlindustry business and management and financial operations2401303.86,664N/AAug 6, 2026
textexpert2411224.22,893N/AAug 6, 2026
textindustry entertainment and sports and media2411241.89,737N/AAug 6, 2026
textmath2411267.55,772N/AAug 6, 2026
text style controlrussian2421292.95,433N/AAug 6, 2026
texthard prompts english2441279.310,078N/AAug 6, 2026
text style controlindustry writing and literature and language2441291.413,818N/AAug 6, 2026
text style controlinstruction following2441292.618,781N/AAug 6, 2026
textoverall2451275.054,698N/AAug 6, 2026
textexclude ties2451200.636,895N/AAug 6, 2026
text style controlindustry software and it services2451339.014,960N/AAug 6, 2026
text style controllonger query2451312.68,294N/AAug 6, 2026
texthard prompts2461258.217,004N/AAug 6, 2026
textrussian2461250.45,433N/AAug 6, 2026
text style controlcoding2461345.78,745N/AAug 6, 2026
textindustry business and management and financial operations2471243.06,664N/AAug 6, 2026
text style controlnon english2491282.924,568N/AAug 6, 2026
textindustry software and it services2511274.914,960N/AAug 6, 2026
textindustry writing and literature and language2511255.413,818N/AAug 6, 2026
textcoding2521268.98,745N/AAug 6, 2026
textlonger query2521256.48,294N/AAug 6, 2026
textinstruction following2531242.818,781N/AAug 6, 2026
text style controlchinese2541291.43,407N/AAug 6, 2026
textnon english2561235.524,568N/AAug 6, 2026
textchinese2631215.53,407N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.129 input, $0.399 output per 1M via Cortecs
Tracked offerings
10
10 rows
Columns

Show columns

Llamallama-3.3-70b-instructglobalN/AN/A128KAug 7, 2026
Cortecsllama-3.3-70b-instructglobal$0.129$0.399131KAug 7, 2026
LLM Gatewayllama-3.3-70b-instructglobal$0.13$0.40131.1KAug 7, 2026
Heliconellama-3.3-70b-instructglobal$0.13$0.39128KAug 7, 2026
Regolo AIllama-3.3-70b-instructglobal$0.60$2.7128KAug 7, 2026
Charm Hyperllama-3.3-70b-instructglobal$0.6066$1.04128KAug 7, 2026
Azure Cognitive Servicesllama-3.3-70b-instructglobal$0.71$0.71128KAug 7, 2026
Azurellama-3.3-70b-instructglobal$0.71$0.71128KAug 7, 2026
Scalewayllama-3.3-70b-instructglobal$0.90$0.90100KAug 7, 2026
GreenPTllama-3.3-70b-instructglobal$1.25$1.25100KAug 7, 2026

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

Llama 3.3 70B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Llama 3.3 70B InstructDec 6, 202454.670B128K4.1KYesLlama 3.3 Community License Agreement

What is Llama 3.3 70B?

A concise description based on the published model registry.

Llama 3.3 is a multilingual large language model optimized for dialogue use cases across multiple languages. It is a pretrained and instruction-tuned generative model with 70 billion parameters, outperforming many open-source and closed chat models on common industry benchmarks. Llama 3.3 supports a context length of 128,000 tokens and is designed for commercial and research use in multiple languages.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Llama 3.3 70B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Llama 3.3 70BvsNova 2 LiteLlama 3.3 70Bvso4 miniLlama 3.3 70BvsMiniMax M2.1Llama 3.3 70BvsQwen3 Next 80B A3B ThinkingLlama 3.3 70BvsQwen3.5 35B A3BLlama 3.3 70BvsQwen2.5 72B

Models similar to Llama 3.3 70B

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

#77-2.2
ME

Llama 3.1 70B

Meta

52.4 LLMBoard

DetailsCompare
#88-6.1
ME

Llama 4 Maverick

Meta

48.5 LLMBoard

DetailsCompare
#31+15.3
ME

Llama 3.1 405B

Meta

69.9 LLMBoard

DetailsCompare
#133-22.2
ME

Llama 4 Scout

Meta

32.3 LLMBoard

DetailsCompare
#137-25.1
ME

Llama 3.1 8B

Meta

29.5 LLMBoard

DetailsCompare
#155-34.2
ME

Llama 3.2 3B

Meta

20.4 LLMBoard

DetailsCompare

FAQ

Common questions about Llama 3.3 70B.

When was Llama 3.3 70B released?

Llama 3.3 70B's default version was released on Dec 6, 2024.

How much does Llama 3.3 70B cost?

No official standard PAYG price is currently available for Llama 3.3 70B. The lowest tracked third-party offer starts at $0.129 input and $0.399 output via Cortecs.

Who created Llama 3.3 70B?

Llama 3.3 70B is published under Meta in the model registry.

What is the context window for Llama 3.3 70B?

The default version has a 128K token context window.

Is Llama 3.3 70B open weight?

Yes. The default version is marked as open weight under Llama 3.3 Community License Agreement.

How many API providers offer Llama 3.3 70B?

10 published provider offerings are linked to the default version.

What models should I compare Llama 3.3 70B with?

Nearby ranked alternatives include Nova 2 Lite, o4 mini, MiniMax M2.1.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai