DeepSeek V3.2 Speciale vs Qwen3 4B
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 56.5)
- •Qwen3 4B is cheaper ($0.10 vs $0.29 per 1M input)
| DeepSeek V3.2 Speciale | Qwen3 4B | |
|---|---|---|
| Intelligence index | 89.9 | 56.5 |
| 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 | $0.40 / 1M |
| Speed | — | 103 tok/s |
| Released | December 1, 2025 | April 28, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Qwen3 4B
AIME 2025
96.7
22.3
GPQA Diamond
87.1
52.2
Humanity’s Last Exam
26.1
5.1
LiveCodeBench
89.6
46.5
MMLU-Pro
86.3
69.6