Comprehensive side-by-side LLM comparison
Llama 3.1 405B Instruct leads with 20.1% higher average benchmark score. Llama 3.2 3B Instruct is $1.75 cheaper per million tokens. Llama 3.1 405B Instruct is available on 8 providers. Overall, Llama 3.1 405B Instruct is the stronger choice for coding tasks.
Meta
Llama 3.1 405B was developed as Meta's largest open-source language model, designed to provide frontier-level capabilities with 405 billion parameters. Built to demonstrate that open-source models can match proprietary systems in capability, it enables researchers and developers to experiment with and deploy a powerful foundation model without licensing restrictions.
Meta
Llama 3.2 3B was created as an ultra-compact open-source model, designed to enable on-device and edge deployment scenarios. Built with just 3 billion parameters while retaining instruction-following abilities, it brings Meta's language technology to mobile devices, IoT applications, and resource-constrained environments.
2 months newer

Llama 3.1 405B Instruct
Meta
2024-07-23

Llama 3.2 3B Instruct
Meta
2024-09-25
Cost per million tokens (USD)

Llama 3.1 405B Instruct

Llama 3.2 3B Instruct
Context window and performance specifications
Average performance across 7 common benchmarks

Llama 3.1 405B Instruct

Llama 3.2 3B Instruct
Available providers and their performance metrics

Llama 3.1 405B Instruct
Bedrock
DeepInfra
Fireworks
Hyperbolic

Llama 3.1 405B Instruct

Llama 3.2 3B Instruct

Llama 3.1 405B Instruct

Llama 3.2 3B Instruct
Lambda
Replicate
Together

Llama 3.2 3B Instruct
DeepInfra