DeepSeek V3.2 Speciale vs Phi 4 Reasoning
DeepSeek vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 66.4)
| DeepSeek V3.2 Speciale | Phi 4 Reasoning | |
|---|---|---|
| Intelligence index | 89.9 | 66.4 |
| Developer | DeepSeek | Microsoft |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | — |
| Output price | $0.43 / 1M | — |
| Speed | — | — |
| Released | December 1, 2025 | April 30, 2025 |
| Parameters | — | 14000000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Phi 4 Reasoning
AIME 2025
96.7
62.9
GPQA Diamond
87.1
65.8
LiveCodeBench
89.6
53.8
MMLU-Pro
86.3
74.3