Model Comparison
Nemotron 3 Super 120B A12B (Reasoning)
vs. Nemotron Nano 9B V2 (Reasoning)
Comparing 2 AI models · 10 benchmarks · NVIDIA
Recommended Pick
NV Nemotron 3 Super 120B A12B (Reasoning) 12 metric wins Strongest on: Throughput, Latency, Reasoning
Best Value
Nemotron Nano 9B V2 (Reasoning)
100.0 value score
43.2 reasoning / $0.07/1M
Lowest Price
Nemotron Nano 9B V2 (Reasoning)
$0.04/1M input price
Best Reasoning
Nemotron 3 Super 120B A12B (Reasoning)
45.1 reasoning score
Blends available reasoning benchmarks
Best for Coding
Nemotron 3 Super 120B A12B (Reasoning)
31.2 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
Nemotron Nano 9B V2 (Reasoning) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Nemotron Nano 9B V2 (Reasoning) is 7.5x cheaper on input tokens than Nemotron 3 Super 120B A12B (Reasoning).
Speed gap
Nemotron 3 Super 120B A12B (Reasoning) generates about 1.3x as many tokens per second as Nemotron Nano 9B V2 (Reasoning).
Reasoning gap
Nemotron 3 Super 120B A12B (Reasoning) leads Nemotron Nano 9B V2 (Reasoning) by 1.9 points on reasoning.
Coding gap
Nemotron 3 Super 120B A12B (Reasoning) leads Nemotron Nano 9B V2 (Reasoning) by 22.9 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Nemotron Nano 9B V2 (Reasoning)
NVIDIA
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick NV Nemotron 3 Super 120B A12B (Reasoning) | NV Nemotron Nano 9B V2 (Reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.30/1M | $0.04/1M |
| Output Cost | $0.75/1M | $0.16/1M |
| Blended (3:1) | $0.41/1M | $0.07/1M |
| Specifications | ||
| Organization | NVIDIA | NVIDIA |
| Release Date | Mar 11, 2026 | Aug 18, 2025 |
| Performance & Speed | ||
| Throughput | 155.1 tok/s | 118.8 tok/s |
| TTFT | 1070ms | 252ms |
| Latency | 13966ms | 17093ms |
| Composite Indices | ||
| Value Score | 17.7 | 100.0 |
| Reasoning Score | 45.1 | 43.2 |
| Intelligence | 36.0 | 14.8 |
| Coding | 31.2 | 8.3 |
| Math | — | 69.7 |
| Standard Benchmarks | ||
| GPQA | 80.0% | 57.0% |
| MMLU Pro | — | 74.2% |
| HLE | 19.2% | 4.6% |
| LiveCodeBench | — | 72.4% |
| AIME 2025 | — | 69.7% |
| SciCode | 36.0% | 22.0% |
| LCR | 60.0% | 21.0% |
| IFBench | 71.5% | 27.6% |
| TAU-bench v2 | 67.8% | 21.9% |
| TerminalBench Hard | 28.8% | 1.5% |
Key Takeaways
Nemotron Nano 9B V2 (Reasoning) offers the best value at $0.04/1M, making it ideal for high-volume applications and cost-conscious projects.
Nemotron 3 Super 120B A12B (Reasoning) has the strongest reasoning profile with a 45.1 reasoning score, combining the available reasoning-heavy benchmarks.
Nemotron 3 Super 120B A12B (Reasoning) reaches a 31.2 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Nemotron 3 Super 120B A12B (Reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Nemotron Nano 9B V2 (Reasoning)
- Cost-sensitive applications
- High-volume processing
