AI Hub
← All models

DeepSeek-V4-Flash vs Phi 4 Mini Instruct

DeepSeek vs Microsoft — benchmarks, pricing, and capabilities side by side.

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 32.6)
  • Phi 4 Mini Instruct is cheaper ($0.08 vs $0.10 per 1M input)
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashPhi 4 Mini Instruct
Intelligence index89.432.6
DeveloperDeepSeekMicrosoft
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens131,072 tokens
Input price$0.10 / 1M$0.08 / 1M
Output price$0.20 / 1M$0.35 / 1M
Speed109 tok/s
ReleasedApril 24, 2026October 17, 2025
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
Phi 4 Mini Instruct
GPQA Diamond
89.4
33.1
Humanity’s Last Exam
32.1
4.2