Comprehensive side-by-side LLM comparison
GPT-4.1 mini leads with 16.6% higher average benchmark score. GPT-4.1 mini offers 680.3K more tokens in context window than Claude 3 Sonnet. GPT-4.1 mini is $16.00 cheaper per million tokens. Overall, GPT-4.1 mini 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 Mini was created as a smaller, more efficient variant of GPT-4.1, designed to provide strong capabilities with reduced computational requirements. Built to serve applications where speed and cost are priorities while maintaining solid performance, it extends the GPT-4.1 capabilities to resource-conscious deployments.
1 year newer

Claude 3 Sonnet
Anthropic
2024-02-29

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

Claude 3 Sonnet

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

Claude 3 Sonnet

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

Claude 3 Sonnet
Anthropic
Bedrock

Claude 3 Sonnet

GPT-4.1 mini

Claude 3 Sonnet

GPT-4.1 mini

GPT-4.1 mini
OpenAI
ZeroEval