How much does Llama 3.2 3B Instruct cost?

Llama 3.2 3B Instruct costs $0.05 per million input tokens and $0.34 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.000 per message.

What benchmarks has Llama 3.2 3B Instruct been tested on?

Llama 3.2 3B Instruct has been evaluated on 7 benchmarks. Top scores: Chatbot Arena Elo — Overall: 1165.7, IFEval: 73.9, MMLU-PRO: 24.4.

Is Llama 3.2 3B Instruct open source?

Yes, Llama 3.2 3B Instruct is open source.

How does Llama 3.2 3B Instruct compare to Qwen2.5-Max?

Llama 3.2 3B Instruct has an average score of 35.9 while Qwen2.5-Max scores 36.0. Qwen2.5-Max slightly outperforms Llama 3.2 3B Instruct overall. See full comparison →

Home/Models/Llama 3.2 3B Instruct

Llama 3.2 3B Instruct

Name: Llama 3.2 3B Instruct
Price: 0.051 USD
Author: Meta

by Meta · Released Sep 2024

Open Source

35.9

avg score

Rank #162

Compare

Better than 30% of all models

Context

80K tokens (~40 books)

Input $/1M

$0.05

Output $/1M

$0.34

Type

text

License

Open Source

Benchmarks

7 tested

Data updated today

About

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Tested on 7 benchmarks with 24.2% average. Top scores: Chatbot Arena Elo — Overall (1165.7%), IFEval (73.9%), MMLU-PRO (24.4%).

Looking for similar performance at lower cost?
Gemma 3 27B (free) scores 35.0 (97% as good) at $0.00/1M input · 100% cheaper

Capabilities

reasoning

1.4

#180 globally

math

17.7

#173 globally

knowledge

14.1

#206 globally

language

73.9

#61 globally

general

24.1

#36 globally

Benchmark Scores

Compare All

Tested on 7 benchmarks · Ranked across 6 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

reasoningCompare reasoning →

MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

1.4—

mathCompare math →

MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

17.7—

knowledgeCompare knowledge →

MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

24.4—

GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

3.8—

Quick compare:

vs Qwen2.5-Max

vs Mistral Large 2411

vs GPT-4o (2024-11-20)

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · Meta Llama 3.2

Llama 3.2 11B Vision InstructSep 2024

$0.24/M in131Kctx

Llama 3.2 1B InstructSep 2024

14.5+14.5

$0.03/M in(-0.22)60Kctx(-71K)7 benchmarks

Llama 3.2 3B InstructSep 2024

24.2+9.7

$0.05/M in(+0.02)80Kctx(+20K)7 benchmarks

Llama 3.2 3B Instruct (free)Sep 2024

8.7-15.5

$0.00/M in(-0.05)131Kctx(+51K)6 benchmarks

Llama 3.2 90BJan 2024

36.1+27.4

N/AN/Actx6 benchmarks

See the full Llama 3.2 family →

Similar Models

Links

Info

Meta Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

llama-3-2-3b-instruct

Specifications

Typetext
Context80K tokens (~40 books)
ReleasedSep 2024
LicenseOpen Source
StatusActive
Cost / Message~$0.000

Available On

Meta$0.05

Frequently Asked Questions

Llama 3.2 3B Instruct is an open-source text AI model by Meta, released in September 2024. It has an average benchmark score of 35.9. Context window: 80K tokens.

Benchmarks

Chatbot Arena Elo — Overall IFEval MMLU-PRO BBH (HuggingFace)MATH Level 5

Meta · Provider Meta · Economy All Models Compare Models Pricing Developers · API

Llama 3.2 3B Instruct

Frequently Asked Questions

Related Models

Benchmarks

Related Pages