AI Hub
← All models

DeepSeek-V4-Flash vs Phi 4

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 47.6)
  • Phi 4 is cheaper ($0.07 vs $0.10 per 1M input)
  • DeepSeek-V4-Flash is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashPhi 4
Intelligence index89.447.6
DeveloperDeepSeekMicrosoft
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens16,384 tokens
Input price$0.10 / 1M$0.07 / 1M
Output price$0.20 / 1M$0.14 / 1M
Speed109 tok/s33 tok/s
ReleasedApril 24, 2026January 10, 2025
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
Phi 4
GPQA Diamond
89.4
56.1
Humanity’s Last Exam
32.1
4.1