Comprehensive side-by-side LLM comparison
GPT-5 leads with 30.2% higher average benchmark score. GPT-5 offers 128.0K more tokens in context window than Claude 3 Sonnet. GPT-5 is $6.75 cheaper per million tokens. Overall, GPT-5 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-5 represents the next generation of OpenAI's foundational models, developed to advance the frontier of AI capabilities in reasoning, knowledge, and general intelligence. Built to push beyond the limitations of GPT-4, it incorporates architectural and training improvements designed to enhance performance across diverse tasks and domains.
1 year newer

Claude 3 Sonnet
Anthropic
2024-02-29

GPT-5
OpenAI
2025-08-07
Cost per million tokens (USD)

Claude 3 Sonnet

GPT-5
Context window and performance specifications
Average performance across 4 common benchmarks

Claude 3 Sonnet

GPT-5
GPT-5
2024-09-30
Available providers and their performance metrics

Claude 3 Sonnet
Anthropic
Bedrock

Claude 3 Sonnet

GPT-5

Claude 3 Sonnet

GPT-5

GPT-5
OpenAI
ZeroEval