DeepSeek V3.2 Speciale vs Ling-flash-2.0
DeepSeek vs InclusionAI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 66.9)
- •Ling-flash-2.0 is cheaper ($0.10 vs $0.29 per 1M input)
| DeepSeek V3.2 Speciale | Ling-flash-2.0 | |
|---|---|---|
| Intelligence index | 89.9 | 66.9 |
| Developer | DeepSeek | InclusionAI |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | $0.10 / 1M |
| Output price | $0.43 / 1M | $0.60 / 1M |
| Speed | — | 91 tok/s |
| Released | December 1, 2025 | September 17, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Ling-flash-2.0
AIME 2025
96.7
65.3
GPQA Diamond
87.1
65.7
Humanity’s Last Exam
26.1
6.3
LiveCodeBench
89.6
58.9
MMLU-Pro
86.3
77.7