Comprehensive side-by-side LLM comparison
Claude 3.7 Sonnet leads with 26.4% higher average benchmark score. Claude 3.7 Sonnet offers 72.0K more tokens in context window than Llama 3.2 90B Instruct. Llama 3.2 90B Instruct is $17.25 cheaper per million tokens. Overall, Claude 3.7 Sonnet is the stronger choice for coding tasks.
Anthropic
Claude 3.7 Sonnet represents Anthropic's first hybrid reasoning model, capable of producing near-instant responses or extended step-by-step thinking that is visible to users. Developed with particularly strong improvements in coding and front-end web development, it allows users to control thinking budgets and balances real-world task performance with reasoning capabilities for enterprise applications.
Meta
Llama 3.2 90B was developed as a flagship-tier open-source model, designed to provide advanced capabilities with 90 billion parameters. Built to serve applications requiring high-quality reasoning and generation, it represents a powerful option within the Llama 3.2 series for demanding tasks.
5 months newer

Llama 3.2 90B Instruct
Meta
2024-09-25

Claude 3.7 Sonnet
Anthropic
2025-02-24
Cost per million tokens (USD)

Claude 3.7 Sonnet

Llama 3.2 90B Instruct
Context window and performance specifications
Average performance across 2 common benchmarks

Claude 3.7 Sonnet

Llama 3.2 90B Instruct
Available providers and their performance metrics

Claude 3.7 Sonnet
Anthropic
Bedrock
ZeroEval

Claude 3.7 Sonnet

Llama 3.2 90B Instruct

Claude 3.7 Sonnet

Llama 3.2 90B Instruct

Llama 3.2 90B Instruct
Bedrock
DeepInfra
Fireworks
Hyperbolic
Together