DeepSeek V3.2 Speciale vs Llama-3.3 Nemotron Super 49B v1
DeepSeek vs NVIDIA — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 63.9)
- •Llama-3.3 Nemotron Super 49B v1 is cheaper ($0.00 vs $0.29 per 1M input)
| DeepSeek V3.2 Speciale | Llama-3.3 Nemotron Super 49B v1 | |
|---|---|---|
| Intelligence index | 89.9 | 63.9 |
| Developer | DeepSeek | NVIDIA |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | — |
| Input price | $0.29 / 1M | $0.00 / 1M |
| Output price | $0.43 / 1M | $0.00 / 1M |
| Speed | — | — |
| Released | December 1, 2025 | March 18, 2025 |
| Parameters | — | 49900000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek V3.2 Speciale
Llama-3.3 Nemotron Super 49B v1
AIME 2025
96.7
58.4
GPQA Diamond
87.1
66.7
Humanity’s Last Exam
26.1
6.5
LiveCodeBench
89.6
28
MMLU-Pro
86.3
78.5