Model Comparison
Claude 3.7 SonnetGPT-5 Codex
Let's see who can write code better - Claude 3.7 Sonnet or GPT-5 Codex
Model Information
Claude 3.7 Sonnet
Description
Enhanced Sonnet model with improved capabilities
Specifications
Context Window200K
Max Output8K
ReleasedDec 2024
API✓
Pricing (per 1M)
In / Out
$3/ $15
Key Features
Enhanced reasoningBetter code generationImproved instruction followingMulti-language support
Strengths
- ✓Balanced performance
- ✓Good context handling
- ✓Reliable outputs
- ✓Improved over 3.5 Sonnet
Weaknesses
- ✗More expensive than Haiku
- ✗Not as powerful as Opus
- ✗Limited availability
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