DeepSeek R1 Distill Qwen 32B vs DeepSeek V3.2 Speciale
DeepSeek vs DeepSeek — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 68.4)
- •DeepSeek R1 Distill Qwen 32B is cheaper ($0.12 vs $0.29 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek R1 Distill Qwen 32B | DeepSeek V3.2 Speciale | |
|---|---|---|
| Intelligence index | 68.4 | 89.9 |
| Developer | DeepSeek | DeepSeek |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 128,000 tokens | 163,840 tokens |
| Input price | $0.12 / 1M | $0.29 / 1M |
| Output price | $0.18 / 1M | $0.43 / 1M |
| Speed | 37 tok/s | — |
| Released | January 20, 2025 | December 1, 2025 |
| Parameters | 32800000000 | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
DeepSeek R1 Distill Qwen 32B
DeepSeek V3.2 Speciale
AIME 2025
63
96.7
GPQA Diamond
62.1
87.1
Humanity’s Last Exam
5.5
26.1
LiveCodeBench
57.2
89.6
MMLU-Pro
73.9
86.3