Comprehensive side-by-side LLM comparison
GPT-5 leads with 25.8% higher average benchmark score. GPT-5 offers 224.7K more tokens in context window than Claude 3.5 Sonnet. Claude 3.5 Sonnet is $132.00 cheaper per million tokens. Claude 3.5 Sonnet is available on 3 providers. Overall, GPT-5 is the stronger choice for coding tasks.
Anthropic
Claude 3.5 Sonnet, updated by Anthropic in October 2024 (originally released June 2024), is a large language model from the Claude 3.5 family that delivered strong performance in coding, reasoning, and instruction-following at its release. It supports a 200K token context window, 8K maximum output tokens, and native image understanding including screenshot analysis and document comprehension. Claude 3.5 Sonnet targets general-purpose development tasks, document analysis, and applications requiring reliable instruction following with visual input support.
OpenAI
GPT-5, released by OpenAI on August 7, 2025, is a large language model that combines direct generation and extended reasoning in a single unified system with a built-in routing mechanism. It features a 400K token context window, 128K maximum output tokens, native multimodal support (text, image, audio, video), and demonstrated strong results across coding, mathematics, visual understanding, and health benchmarks at release. GPT-5 targets complex multi-step tasks including advanced coding, mathematical problem solving, and long-context analysis.
9 months newer

Claude 3.5 Sonnet
Anthropic
2024-10-22

GPT-5
OpenAI
2025-08-07
Cost per million tokens (USD)
Claude 3.5 Sonnet
GPT-5
Context window and performance specifications
Average performance across 2 common benchmarks
Claude 3.5 Sonnet
GPT-5
Performance comparison across key benchmark categories
Claude 3.5 Sonnet
GPT-5
Claude 3.5 Sonnet
2024-04
GPT-5
2025-05
Available providers and their performance metrics
Claude 3.5 Sonnet
Anthropic
AWS Bedrock
Google Cloud Vertex AI
GPT-5
Claude 3.5 Sonnet
GPT-5
Claude 3.5 Sonnet
GPT-5
OpenAI