AI Hub
← All models

GPT-5.2-Codex vs Mistral Medium 3.5

OpenAI vs Mistral AI — benchmarks, pricing, and capabilities side by side.

  • GPT-5.2-Codex has the higher intelligence index (89.9 vs 74.8)
  • Mistral Medium 3.5 is cheaper ($1.50 vs $1.75 per 1M input)
  • Mistral Medium 3.5 is faster
  • GPT-5.2-Codex has a larger context window (400K)
GPT-5.2-CodexMistral Medium 3.5
Intelligence index89.974.8
DeveloperOpenAIMistral AI
TypeMultimodalMultimodal
AccessAPI onlyAPI only
Context window400,000 tokens262,144 tokens
Input price$1.75 / 1M$1.50 / 1M
Output price$14.00 / 1M$7.50 / 1M
Speed106 tok/s140 tok/s
ReleasedJanuary 14, 2026April 30, 2026
Parameters
Input modalitiesText, ImageText, Image
Output modalitiesTextText

Shared benchmarks

GPT-5.2-Codex
Mistral Medium 3.5
GPQA Diamond
89.9
74.8
Humanity’s Last Exam
33.5
12.8