DeepSeek V3.2 Speciale vs Kimi K2 Thinking
DeepSeek vs Moonshot AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 85.6)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.60 per 1M input)
- •Kimi K2 Thinking has a larger context window (262K)
| DeepSeek V3.2 Speciale | Kimi K2 Thinking | |
|---|---|---|
| Intelligence index | 89.9 | 85.6 |
| Developer | DeepSeek | Moonshot AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| 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 | — | 100 tok/s |
| Released | December 1, 2025 | November 6, 2025 |
| Parameters | — | 1T (32B active) |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek V3.2 Speciale
Kimi K2 Thinking
AIME 2025
96.7
94.7
GPQA Diamond
87.1
84.5
Humanity’s Last Exam
26.1
22.3
LiveCodeBench
89.6
85.3
MMLU-Pro
86.3
84.8