DeepSeek V3.2 Speciale vs Phi-3.5-mini-instruct
DeepSeek vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 46)
- •Phi-3.5-mini-instruct is cheaper ($0.10 vs $0.29 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | Phi-3.5-mini-instruct | |
|---|---|---|
| Intelligence index | 89.9 | 46 |
| Developer | DeepSeek | Microsoft |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 128,000 tokens |
| Input price | $0.29 / 1M | $0.10 / 1M |
| Output price | $0.43 / 1M | $0.10 / 1M |
| Speed | — | 23 tok/s |
| Released | December 1, 2025 | August 23, 2024 |
| Parameters | — | 3800000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Phi-3.5-mini-instruct
GPQA Diamond
87.1
30.4
MMLU-Pro
86.3
47.4