Model Comparison
Claude 4 SonnetGPT-5 Codex
Let's see who can write code better - Claude 4 Sonnet or GPT-5 Codex
Model Information
Claude 4 Sonnet
Description
Balanced Claude 4 model with excellent performance
Specifications
Context Window200K
Max Output8K
ReleasedJan 2025
API✓
Pricing (per 1M)
In / Out
$3/ $15
Key Features
Balanced performanceAdvanced reasoningCode generationMulti-modal capabilities
Strengths
- ✓Good price-performance ratio
- ✓Versatile capabilities
- ✓Fast inference
- ✓Strong at most tasks
Weaknesses
- ✗Not as powerful as Opus
- ✗Higher cost than Haiku
- ✗May struggle with very complex tasks
Agent Support
GPT-5 Codex
Description
Flagship model from OpenAI optimised for coding tasks
Specifications
Context Window272K
Max Output33K
ReleasedSep 2025
API✗
Pricing (per 1M)
In / Out
$1.25/ $10
Key Features
CodingAdvanced reasoningMulti-modal native
Strengths
- ✓State-of-the-art performance
- ✓Optimised for coding
- ✓Large context window
Weaknesses
- ✗Likely very expensive
- ✗Unknown specifications
Agent Support
No known agents