Comprehensive side-by-side LLM comparison
Claude Sonnet 4.6 leads with 13.8% higher average benchmark score. GPT-5 Mini offers 168.8K more tokens in context window than Claude Sonnet 4.6. Claude Sonnet 4.6 is $7.00 cheaper per million tokens. Claude Sonnet 4.6 is available on 3 providers. Overall, Claude Sonnet 4.6 is the stronger choice for coding tasks.
Anthropic
Claude Sonnet 4.6 is a general-purpose language model from Anthropic, released in February 2026 as an update to the Sonnet 4 line that introduced adaptive thinking — a mode where the model automatically calibrates its reasoning depth based on task complexity rather than requiring manual configuration by the developer. The model accepts text and image inputs and integrates natively with web search and code execution tools, consolidating capabilities that previously required separate toolchain setup into a unified API surface. It became the primary workhorse model in the Claude 4 series for code assistance, agentic pipelines, and retrieval-augmented applications that benefit from built-in web access.
OpenAI
GPT-5 mini, released by OpenAI in August 2025, is a smaller variant from the GPT-5 family that inherits GPT-5's unified reasoning architecture and multimodal capabilities at a reduced inference cost. It targets high-volume production use cases requiring a balance of intelligence and response speed, offering GPT-5 capabilities for applications where full GPT-5 inference costs are a concern.
6 months newer

GPT-5 Mini
OpenAI
2025-08

Claude Sonnet 4.6
Anthropic
2026-02-17
Cost per million tokens (USD)
Claude Sonnet 4.6
GPT-5 Mini
Context window and performance specifications
Average performance across 1 common benchmarks
Claude Sonnet 4.6
GPT-5 Mini
Performance comparison across key benchmark categories
Claude Sonnet 4.6
GPT-5 Mini
Claude Sonnet 4.6
2025-08
Available providers and their performance metrics
Claude Sonnet 4.6
Anthropic
AWS Bedrock
Google Cloud Vertex AI
GPT-5 Mini
Claude Sonnet 4.6
GPT-5 Mini
Claude Sonnet 4.6
GPT-5 Mini
OpenAI