GPT-5.1 Codex vs Claude 4 Sonnet (thinking)
Detailed comparison of capabilities, features, and performance.
Feature
GPT-5.1 Codex
Claude 4 Sonnet (thinking)
Model Image
AI Lab
OpenAI
Anthropic
Context Size
400,000 tokens
200,000 tokens
Max Output Size
128,000 tokens
64,000 tokens
Frontier Model
Yes
Yes
Vision Support
Yes
Yes
Description
A version of GPT-5.1 optimized for agentic coding tasks in Codex or similar environments.
The latest Sonnet 4 model from Anthropic with high thinking mode
Learn more about GPT-5.1 Codex
View detailed specifications and capabilities
View model details →Learn more about Claude 4 Sonnet (thinking)
View detailed specifications and capabilities
View model details →More model comparisons
Try both models in your workspace
Access both GPT-5.1 Codex and Claude 4 Sonnet (thinking) in a single workspace without managing multiple API keys.
Create your workspace