DeepSeek V3.2 Speciale vs Kimi K2 0905
DeepSeek vs Moonshot AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 71)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.60 per 1M input)
- •Kimi K2 0905 has a larger context window (262K)
| DeepSeek V3.2 Speciale | Kimi K2 0905 | |
|---|---|---|
| Intelligence index | 89.9 | 71 |
| Developer | DeepSeek | Moonshot AI |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 163,840 tokens | 262,144 tokens |
| Input price | $0.29 / 1M | $0.60 / 1M |
| Output price | $0.43 / 1M | $2.50 / 1M |
| Speed | — | 16 tok/s |
| Released | December 1, 2025 | September 5, 2025 |
| Parameters | — | 1000000000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Kimi K2 0905
AIME 2025
96.7
57.3
GPQA Diamond
87.1
75.8
Humanity’s Last Exam
26.1
6.3
LiveCodeBench
89.6
61
MMLU-Pro
86.3
82.5