AI Hub
← All models

DeepSeek V3.2 Speciale vs Phi-3 Mini Instruct 3.8B

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 27.5)
  • Phi-3 Mini Instruct 3.8B is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek V3.2 SpecialePhi-3 Mini Instruct 3.8B
Intelligence index89.927.5
DeveloperDeepSeekMicrosoft
TypeLLMLLM
AccessOpen weights
Context window163,840 tokens
Input price$0.29 / 1M$0.00 / 1M
Output price$0.43 / 1M$0.00 / 1M
Speed
ReleasedDecember 1, 2025April 23, 2024
Parameters
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek V3.2 Speciale
Phi-3 Mini Instruct 3.8B
AIME 2025
96.7
0.3
GPQA Diamond
87.1
31.9
Humanity’s Last Exam
26.1
4.4
LiveCodeBench
89.6
11.6
MMLU-Pro
86.3
43.5