DeepSeek V3.2 Speciale vs Devstral Small 2
DeepSeek vs Mistral AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 47.5)
- •Devstral Small 2 is cheaper ($0.00 vs $0.29 per 1M input)
| DeepSeek V3.2 Speciale | Devstral Small 2 | |
|---|---|---|
| Intelligence index | 89.9 | 47.5 |
| Developer | DeepSeek | Mistral AI |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | $0.00 / 1M |
| Output price | $0.43 / 1M | $0.00 / 1M |
| Speed | — | 62 tok/s |
| Released | December 1, 2025 | December 9, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Devstral Small 2
AIME 2025
96.7
34.3
GPQA Diamond
87.1
53.2
Humanity’s Last Exam
26.1
3.4
LiveCodeBench
89.6
34.8
MMLU-Pro
86.3
67.8