DeepSeek V3.2 Speciale vs Qwen3 0.6B
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 29.3)
- •Qwen3 0.6B is cheaper ($0.10 vs $0.29 per 1M input)
| DeepSeek V3.2 Speciale | Qwen3 0.6B | |
|---|---|---|
| Intelligence index | 89.9 | 29.3 |
| Developer | DeepSeek | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | $0.10 / 1M |
| Output price | $0.43 / 1M | $1.30 / 1M |
| Speed | — | 225 tok/s |
| Released | December 1, 2025 | April 28, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Qwen3 0.6B
AIME 2025
96.7
18
GPQA Diamond
87.1
23.9
Humanity’s Last Exam
26.1
5.7
LiveCodeBench
89.6
12.1
MMLU-Pro
86.3
34.7