AI Hub
← All models

DeepSeek-V4-Flash vs Phi-3.5-mini-instruct

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 46)
  • DeepSeek-V4-Flash is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashPhi-3.5-mini-instruct
Intelligence index89.446
DeveloperDeepSeekMicrosoft
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens128,000 tokens
Input price$0.10 / 1M$0.10 / 1M
Output price$0.20 / 1M$0.10 / 1M
Speed109 tok/s23 tok/s
ReleasedApril 24, 2026August 23, 2024
Parameters284B (13B active)3800000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-V4-Flash
Phi-3.5-mini-instruct
GPQA Diamond
89.4
30.4