DeepSeek-R1 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 75)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.55 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek-R1 | DeepSeek V3.2 Speciale | |
|---|---|---|
| Intelligence index | 75 | 89.9 |
| Developer | DeepSeek | DeepSeek |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 128,000 tokens | 163,840 tokens |
| Input price | $0.55 / 1M | $0.29 / 1M |
| Output price | $2.19 / 1M | $0.43 / 1M |
| Speed | 189 tok/s | — |
| Released | January 20, 2025 | December 1, 2025 |
| Parameters | 671B total / 37B active (MoE) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-R1
DeepSeek V3.2 Speciale
AIME 2025
68
96.7
GPQA Diamond
71.5
87.1
Humanity’s Last Exam
9.3
26.1
LiveCodeBench
61.7
89.6
MMLU-Pro
84.4
86.3