NVIDIA Nemotron Nano 9B V2 (Reasoning) vs NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
Comparing 2 AI models · 5 benchmarks · NVIDIA
Most Affordable
NV
NVIDIA Nemotron Nano 9B V2 (Reasoning)
$0.04/1M
Highest Intelligence
NV
NVIDIA Nemotron Nano 9B V2 (Reasoning)
57.0% GPQA
Best for Coding
NV
NVIDIA Nemotron Nano 9B V2 (Reasoning)
31.9 Coding Index
Price Difference
1.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
5 tests
NV
NVIDIA Nemotron Nano 9B V2 (Reasoning)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
NV
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
0
No clear wins
| Metric | NV NVIDIA Nemotron Nano 9B V2 (Reasoning) | NV NVIDIA Nemotron Nano 9B V2 (Non-reasoning) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.04/1M | $0.04/1M |
| Output Cost | $0.16/1M | $0.16/1M |
| Blended Cost 3:1 input/output ratio | $0.07/1M | $0.07/1M |
| Specifications | ||
| Organization Model creator | NVIDIA | NVIDIA |
| Release Date Launch date | Aug 18, 2025 | Aug 18, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 95.1 tok/s | 96.4 tok/s |
| Time to First Token (TTFT) Initial response delay | 225ms | 210ms |
| Latency Time to first answer token | 21261ms | 210ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 37.2 | 36.1 |
| Coding Index Programming ability | 31.9 | 30.6 |
| Math Index Mathematical reasoning | 69.7 | 62.3 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 57.0% | 55.7% |
| MMLU Pro Advanced knowledge | 74.2% | 73.9% |
| HLE Hard language evaluation | ||