DeepSeek V3.2 Speciale vs Hermes 3 - Llama-3.1 70B
DeepSeek vs Nous Research — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 42.5)
- •DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.30 per 1M input)
| DeepSeek V3.2 Speciale | Hermes 3 - Llama-3.1 70B | |
|---|---|---|
| Intelligence index | 89.9 | 42.5 |
| Developer | DeepSeek | Nous Research |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | $0.30 / 1M |
| Output price | $0.43 / 1M | $0.30 / 1M |
| Speed | — | 32 tok/s |
| Released | December 1, 2025 | August 15, 2024 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Hermes 3 - Llama-3.1 70B
GPQA Diamond
87.1
40.1
Humanity’s Last Exam
26.1
4.1
LiveCodeBench
89.6
18.8
MMLU-Pro
86.3
57.1