DeepSeek V3.2 Speciale vs Qwen3-235B-A22B-Thinking-2507
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 79.6)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.30 per 1M input)
- •Qwen3-235B-A22B-Thinking-2507 has a larger context window (256K)
| DeepSeek V3.2 Speciale | Qwen3-235B-A22B-Thinking-2507 | |
|---|---|---|
| Intelligence index | 89.9 | 79.6 |
| Developer | DeepSeek | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 256,000 tokens |
| Input price | $0.29 / 1M | $0.30 / 1M |
| Output price | $0.43 / 1M | $3.00 / 1M |
| Speed | — | — |
| Released | December 1, 2025 | July 25, 2025 |
| Parameters | — | 235000000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Qwen3-235B-A22B-Thinking-2507
AIME 2025
96.7
92.3
GPQA Diamond
87.1
81.1
Humanity’s Last Exam
26.1
18.2
MMLU-Pro
86.3
84.4