DeepSeek V3.2 Speciale vs Gemini 1.0 Pro
DeepSeek vs Google — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 34)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.50 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | Gemini 1.0 Pro | |
|---|---|---|
| Intelligence index | 89.9 | 34 |
| Developer | DeepSeek | |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 163,840 tokens | 32,760 tokens |
| Input price | $0.29 / 1M | $0.50 / 1M |
| Output price | $0.43 / 1M | $1.50 / 1M |
| Speed | — | 120 tok/s |
| Released | December 1, 2025 | February 15, 2024 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Gemini 1.0 Pro
GPQA Diamond
87.1
27.9
Humanity’s Last Exam
26.1
4.6
LiveCodeBench
89.6
11.6
MMLU-Pro
86.3
43.1