Compare models

Up to four models side by side.

Compare models
GPT-5.2-Codex OpenAI Deprecated Ministral 3 14B Mistral AI
Context window 400k, Best in row 256k
Max output 128k No data
Output speed 97.2, Best in row 83.1
Quality 79.2, Best in row 21.4
Reasoning 62.8, Best in row 30.9
Coding 60.7, Best in row 17.1
Vision ✓ ✓
Reasoning ✓ −
Tool calling ✓ ✓
Structured output ✓ −
Batch API ✓ −
Self-hostable − ✓
Licence Proprietary Open weights
API model id gpt-5.2-codex ministral-14b-2512

At a glance

Popular comparisons

Head-to-head pages for models people weigh against each other.

Language models 77
Image generation 18
Video generation 11
Text to speech 9
Speech to text 25
Voice and realtime 17
Embeddings 3