Key Takeaways
Phi-3 Mini 128K Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
- Higher intelligence benchmark
Llama 3.1 Nemotron 70B Instruct wins:
- Larger context window
- Faster response time
- Better at coding
- Better at math
Price Advantage
Phi-3 Mini 128K Instruct
Benchmark Advantage
Llama 3.1 Nemotron 70B Instruct
Context Window
Llama 3.1 Nemotron 70B Instruct
Speed
Llama 3.1 Nemotron 70B Instruct
Pricing Comparison
Price Comparison
| Metric | Phi-3 Mini 128K Instruct | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.10 | $0.90 | Phi-3 Mini 128K Instruct |
| Output (per 1M tokens) | $0.10 | $0.90 | Phi-3 Mini 128K Instruct |
| Cache Read (per 1M) | N/A | $0.45 | Llama 3.1 Nemotron 70B Instruct |
Using a 3:1 input/output ratio, Phi-3 Mini 128K Instruct is 89% cheaper overall.
Phi-3 Mini 128K Instruct Providers
No provider data available
Llama 3.1 Nemotron 70B Instruct Providers
No provider data available
Benchmark Comparison
9
Benchmarks Compared
1
Phi-3 Mini 128K Instruct Wins
2
Llama 3.1 Nemotron 70B Instruct Wins
Benchmark Scores
| Benchmark | Phi-3 Mini 128K Instruct | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 26.3 | 13.4 | |
Coding Index Code generation & understanding | - | 10.8 | - |
Math Index Mathematical reasoning | - | 11.0 | - |
MMLU Pro Academic knowledge | 30.4 | 69.0 | |
GPQA Graduate-level science | 9.1 | 46.5 | |
LiveCodeBench Competitive programming | - | 16.9 | - |
Aider Real-world code editing | - | 54.9 | - |
AIME Competition math | - | 24.7 | - |
BBH Big-Bench Hard | 37.1 | - | - |
Llama 3.1 Nemotron 70B Instruct significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Phi-3 Mini 128K Instruct
Other models
Context & Performance
Context Window
Phi-3 Mini 128K Instruct
128,000
tokens
Llama 3.1 Nemotron 70B Instruct
131,072
tokens
Llama 3.1 Nemotron 70B Instruct has a 2% larger context window.
Speed Performance
| Metric | Phi-3 Mini 128K Instruct | Llama 3.1 Nemotron 70B Instruct | Winner |
|---|---|---|---|
| Tokens/second | N/A | 35.5 tok/s | |
| Time to First Token | N/A | 0.51s |
Capabilities
Feature Comparison
| Feature | Phi-3 Mini 128K Instruct | 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 | Phi-3 Mini 128K Instruct | Llama 3.1 Nemotron 70B Instruct |
|---|---|---|
| License | Open Source | Proprietary |
| Author | Microsoft | Nvidia |
| Released | Unknown | Oct 2024 |
Phi-3 Mini 128K Instruct Modalities
Input
Output
Llama 3.1 Nemotron 70B Instruct Modalities
Input
text
Output
text