AI Hub
← All models

DeepSeek-V4-Flash vs Mistral Small 3 24B Instruct

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 62.1)
  • Mistral Small 3 24B Instruct is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashMistral Small 3 24B Instruct
Intelligence index89.462.1
DeveloperDeepSeekMistral AI
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens32,000 tokens
Input price$0.10 / 1M$0.10 / 1M
Output price$0.20 / 1M$0.30 / 1M
Speed109 tok/s134 tok/s
ReleasedApril 24, 2026January 30, 2025
Parameters284B (13B active)24000000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-V4-Flash
Mistral Small 3 24B Instruct
GPQA Diamond
89.4
45.3