AI Hub
← All models

DeepSeek-V4-Flash vs Magistral Small 1.2

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 73.9)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.50 per 1M input)
  • DeepSeek-V4-Flash is faster
DeepSeek-V4-FlashMagistral Small 1.2
Intelligence index89.473.9
DeveloperDeepSeekMistral AI
TypeLLMLLM
AccessOpen weights
Context window1,048,576 tokens
Input price$0.10 / 1M$0.50 / 1M
Output price$0.20 / 1M$1.50 / 1M
Speed109 tok/s106 tok/s
ReleasedApril 24, 2026September 17, 2025
Parameters284B (13B active)
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-V4-Flash
Magistral Small 1.2
GPQA Diamond
89.4
66.3
Humanity’s Last Exam
32.1
6.1