DeepSeek V3.2 Speciale vs Mixtral 8x22B Instruct
DeepSeek vs Mistral AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 39.1)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $2.00 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | Mixtral 8x22B Instruct | |
|---|---|---|
| Intelligence index | 89.9 | 39.1 |
| Developer | DeepSeek | Mistral AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 65,536 tokens |
| Input price | $0.29 / 1M | $2.00 / 1M |
| Output price | $0.43 / 1M | $6.00 / 1M |
| Speed | — | — |
| Released | December 1, 2025 | April 17, 2024 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek V3.2 Speciale
Mixtral 8x22B Instruct
GPQA Diamond
87.1
33.2
Humanity’s Last Exam
26.1
4.1
LiveCodeBench
89.6
14.8
MMLU-Pro
86.3
53.7