DeepSeek V3.2 Speciale vs o1-mini
DeepSeek vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 70.5)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $3.00 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | o1-mini | |
|---|---|---|
| Intelligence index | 89.9 | 70.5 |
| Developer | DeepSeek | OpenAI |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 163,840 tokens | 128,000 tokens |
| Input price | $0.29 / 1M | $3.00 / 1M |
| Output price | $0.43 / 1M | $12.00 / 1M |
| Speed | — | 115 tok/s |
| Released | December 1, 2025 | September 12, 2024 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
o1-mini
GPQA Diamond
87.1
60
Humanity’s Last Exam
26.1
4.9
LiveCodeBench
89.6
57.6
MMLU-Pro
86.3
74.2