DeepSeek V3.2 Speciale vs Qwen3 Next 80B A3B Instruct
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 68.9)
- •Qwen3 Next 80B A3B Instruct is cheaper ($0.09 vs $0.29 per 1M input)
- •Qwen3 Next 80B A3B Instruct has a larger context window (262K)
| DeepSeek V3.2 Speciale | Qwen3 Next 80B A3B Instruct | |
|---|---|---|
| Intelligence index | 89.9 | 68.9 |
| Developer | DeepSeek | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 262,144 tokens |
| Input price | $0.29 / 1M | $0.09 / 1M |
| Output price | $0.43 / 1M | $1.10 / 1M |
| Speed | — | 161 tok/s |
| Released | December 1, 2025 | September 11, 2025 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek V3.2 Speciale
Qwen3 Next 80B A3B Instruct
AIME 2025
96.7
69.5
GPQA Diamond
87.1
72.9
Humanity’s Last Exam
26.1
7.3
LiveCodeBench
89.6
68.4
MMLU-Pro
86.3
80.6