Key Takeaways
Nova Premier 1.0 wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Supports vision
Llama 3.1 Nemotron 70B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
Price Advantage
Llama 3.1 Nemotron 70B Instruct
Benchmark Advantage
Nova Premier 1.0
Context Window
Nova Premier 1.0
Speed
Nova Premier 1.0
Pricing Comparison
Price Comparison
| Metric | Nova Premier 1.0 | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $2.50 | $0.90 | Llama 3.1 Nemotron 70B Instruct |
| Output (per 1M tokens) | $12.50 | $0.90 | Llama 3.1 Nemotron 70B Instruct |
| Cache Read (per 1M) | $0.63 | $0.45 | Llama 3.1 Nemotron 70B Instruct |
Using a 3:1 input/output ratio, Llama 3.1 Nemotron 70B Instruct is 82% cheaper overall.
Nova Premier 1.0 Providers
No provider data available
Llama 3.1 Nemotron 70B Instruct Providers
No provider data available
Benchmark Comparison
8
Benchmarks Compared
6
Nova Premier 1.0 Wins
1
Llama 3.1 Nemotron 70B Instruct Wins
Benchmark Scores
| Benchmark | Nova Premier 1.0 | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 19.0 | 13.4 | |
Coding Index Code generation & understanding | 13.8 | 10.8 | |
Math Index Mathematical reasoning | 17.3 | 11.0 | |
MMLU Pro Academic knowledge | 73.3 | 69.0 | |
GPQA Graduate-level science | 56.9 | 46.5 | |
LiveCodeBench Competitive programming | 31.7 | 16.9 | |
Aider Real-world code editing | - | 54.9 | - |
AIME Competition math | 17.0 | 24.7 |
Nova Premier 1.0 shows stronger mathematical reasoning abilities.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Nova Premier 1.0
Other models
Context & Performance
Context Window
Nova Premier 1.0
1,000,000
tokens
Llama 3.1 Nemotron 70B Instruct
131,072
tokens
Nova Premier 1.0 has a 87% larger context window.
Speed Performance
| Metric | Nova Premier 1.0 | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
| Tokens/second | 72.2 tok/s | 35.5 tok/s | |
| Time to First Token | 0.84s | 0.51s |
Nova Premier 1.0 responds 103% faster on average.
Capabilities
Feature Comparison
| Feature | Nova Premier 1.0 | Llama 3.1 Nemotron 70B Instruct |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Nova Premier 1.0 | Llama 3.1 Nemotron 70B Instruct |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | Amazon | Nvidia |
| Released | Oct 2025 | Oct 2024 |
Nova Premier 1.0 Modalities
Input
textimage
Output
text
Llama 3.1 Nemotron 70B Instruct Modalities
Input
text
Output
text