Key Takeaways
Phi-3 Medium 128K Instruct wins:
- Higher intelligence benchmark
Llama 3.3 Nemotron Super 49B V1.5 wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Better at coding
- Better at math
- Has reasoning mode
Price Advantage
Llama 3.3 Nemotron Super 49B V1.5
Benchmark Advantage
Llama 3.3 Nemotron Super 49B V1.5
Context Window
Llama 3.3 Nemotron Super 49B V1.5
Speed
Llama 3.3 Nemotron Super 49B V1.5
Pricing Comparison
Price Comparison
| Metric | Phi-3 Medium 128K Instruct | Llama 3.3 Nemotron Super 49B V1.5 | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.00 | $0.10 | Llama 3.3 Nemotron Super 49B V1.5 |
| Output (per 1M tokens) | $1.00 | $0.40 | Llama 3.3 Nemotron Super 49B V1.5 |
Using a 3:1 input/output ratio, Llama 3.3 Nemotron Super 49B V1.5 is 83% cheaper overall.
Phi-3 Medium 128K Instruct Providers
No provider data available
Llama 3.3 Nemotron Super 49B V1.5 Providers
No provider data available
Benchmark Comparison
8
Benchmarks Compared
1
Phi-3 Medium 128K Instruct Wins
2
Llama 3.3 Nemotron Super 49B V1.5 Wins
Benchmark Scores
| Benchmark | Phi-3 Medium 128K Instruct | Llama 3.3 Nemotron Super 49B V1.5 | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 32.0 | 14.6 | |
Coding Index Code generation & understanding | - | 10.5 | - |
Math Index Mathematical reasoning | - | 8.0 | - |
MMLU Pro Academic knowledge | 41.2 | 69.2 | |
GPQA Graduate-level science | 11.5 | 48.1 | |
LiveCodeBench Competitive programming | - | 29.0 | - |
AIME Competition math | - | 13.7 | - |
BBH Big-Bench Hard | 48.5 | - | - |
Llama 3.3 Nemotron Super 49B V1.5 significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Phi-3 Medium 128K Instruct
Other models
Context & Performance
Context Window
Phi-3 Medium 128K Instruct
128,000
tokens
Llama 3.3 Nemotron Super 49B V1.5
131,072
tokens
Llama 3.3 Nemotron Super 49B V1.5 has a 2% larger context window.
Speed Performance
| Metric | Phi-3 Medium 128K Instruct | Llama 3.3 Nemotron Super 49B V1.5 | Winner |
|---|---|---|---|
| Tokens/second | N/A | 82.7 tok/s | |
| Time to First Token | N/A | 0.24s |
Capabilities
Feature Comparison
| Feature | Phi-3 Medium 128K Instruct | Llama 3.3 Nemotron Super 49B V1.5 |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Phi-3 Medium 128K Instruct | Llama 3.3 Nemotron Super 49B V1.5 |
|---|---|---|
| License | Open Source | Proprietary |
| Author | Microsoft | Nvidia |
| Released | Unknown | Oct 2025 |
Phi-3 Medium 128K Instruct Modalities
Input
Output
Llama 3.3 Nemotron Super 49B V1.5 Modalities
Input
text
Output
text