Comprehensive side-by-side LLM comparison
GPT-4.1 nano leads with 5.5% higher average benchmark score. GPT-4.1 nano offers 680.3K more tokens in context window than Claude 3 Sonnet. GPT-4.1 nano is $17.50 cheaper per million tokens. Claude 3 Sonnet is available on 3 providers. Overall, GPT-4.1 nano is the stronger choice for coding tasks.
Anthropic
Claude 3 Sonnet was introduced as the balanced middle tier of the Claude 3 family, offering a combination of strong capabilities and operational speed. Designed to provide an optimal tradeoff between intelligence and performance for everyday tasks, it served as a versatile solution for a wide range of enterprise and consumer applications.
OpenAI
GPT-4.1 Nano was developed as the smallest and most efficient variant in the GPT-4.1 family, designed for applications requiring minimal latency and resource usage. Built to enable AI capabilities on edge devices and resource-constrained environments, it distills GPT-4.1 capabilities into an ultra-compact form factor.
1 year newer

Claude 3 Sonnet
Anthropic
2024-02-29

GPT-4.1 nano
OpenAI
2025-04-14
Cost per million tokens (USD)

Claude 3 Sonnet

GPT-4.1 nano
Context window and performance specifications
Average performance across 2 common benchmarks

Claude 3 Sonnet

GPT-4.1 nano
GPT-4.1 nano
2024-05-31
Available providers and their performance metrics

Claude 3 Sonnet
Anthropic
Bedrock

Claude 3 Sonnet

GPT-4.1 nano

Claude 3 Sonnet

GPT-4.1 nano

GPT-4.1 nano
OpenAI