NVIDIA
NVIDIA Nemotron Nano 9B V2 (Reasoning)
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
NVIDIA model catalogModel Snapshot
ReleaseAug 18, 2025
Context128,000
Overall
Rank #424 across 600
8.8
Coding
No rank
n/a
Blended Price
Rank #10 across 379
$0.070/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed236.2 tok/s
First Token3.45s
Max Outputn/a
Pricing
Blended$0.070/M
Input$0.040/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 8.8 | #424 |
| Artificial Analysis Math Index | math | 69.7 | #97 |
| MMLU-Pro | reasoning | 74.2% | #166 |
| GPQA | reasoning | 57.0% | #370 |
| Humanity's Last Exam |