NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Meta Llama 3 8B
Meta logo

Meta Llama 3 8B

by Meta · Released Apr 2024

Open Source
64.0
avg score
Rank #64
Compare
Better than 79% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
11 tested
Data as of
About

Meta-llama text generation model. 3539K downloads on HuggingFace.

Tested on 11 benchmarks · BenchGecko score 64.0. Top scores: JSQuAD (88.9%), JCommonsenseQA (82.9%), JNLI (60.9%).

Capabilities
reasoning
16.0
#150 globally
math
18.6
#232 globally
knowledge
30.5
#240 globally
language
57.0
#113 globally
general
48.7
#35 globally
Benchmark Scores
Compare All
Tested on 11 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR

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

16.0·
mathCompare math →
MATH Level 5

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

18.6·
knowledgeCompare knowledge →
MMLU-PRO

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

41.2·
GPQA

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

19.7·
Quick compare:Alibaba logovs Qwen2.5 Coder 14B Instructz-ai logovs GLM 5OpenAI logovs GPT-4 (older v0314)
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Alibaba logo
Qwen2.5 Coder 14B Instruct
Alibaba
64.1n/a
z-ai logo
GLM 5
z-ai
64.1$0.60/1M
OpenAI logo
GPT-4 (older v0314)
OpenAI
63.8$30.00/1M
Links
Info
MetaPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Meta
Source Code
GitHubHugging Face
BenchGecko API
meta-llama-meta-llama-3-8b
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedApr 2024
  • LicenseOpen Source
  • StatusActive
Available On
Meta logoMetan/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba logoQwen2.5 Coder 14B Instruct
64.1
z-ai logoGLM 5
64.1
OpenAI logoGPT-4 (older v0314)
63.8
z-ai logoGLM 5.1
63.8
Meta Llama 3 8B is an open-source text-generation AI model by Meta, released in April 2024. It has an average benchmark score of 64.0.

Related Models

Qwen2.5 Coder 14B Instruct · AlibabaGLM 5 · z-aiGPT-4 (older v0314) · OpenAIGLM 5.1 · z-aiFalcon 2 11B · TII

Benchmarks

JSQuADJCommonsenseQAJNLILLM-JP — OverallBBH (HuggingFace)

Related Pages

Meta · ProviderMeta · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Meta Llama 3 8B by Meta. BenchGecko score 64.0, rank 64 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Meta Llama 3 8B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/meta-llama-meta-llama-3-8b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP