DeepSeek V3.2 Speciale vs Phi 4 Mini Instruct
DeepSeek vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 32.6)
- •Phi 4 Mini Instruct is cheaper ($0.08 vs $0.29 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | Phi 4 Mini Instruct | |
|---|---|---|
| Intelligence index | 89.9 | 32.6 |
| Developer | DeepSeek | Microsoft |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 131,072 tokens |
| Input price | $0.29 / 1M | $0.08 / 1M |
| Output price | $0.43 / 1M | $0.35 / 1M |
| Speed | — | — |
| Released | December 1, 2025 | October 17, 2025 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek V3.2 Speciale
Phi 4 Mini Instruct
AIME 2025
96.7
6.7
GPQA Diamond
87.1
33.1
Humanity’s Last Exam
26.1
4.2
LiveCodeBench
89.6
12.6
MMLU-Pro
86.3
46.5