Key Takeaways
Llama 3.1 405B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Better at coding
- Better at math
Phi-3 Medium 128K Instruct wins:
- Higher intelligence benchmark
Price Advantage
Llama 3.1 405B Instruct
Benchmark Advantage
Llama 3.1 405B Instruct
Context Window
Llama 3.1 405B Instruct
Speed
Llama 3.1 405B Instruct
Pricing Comparison
Price Comparison
| Metric | Llama 3.1 405B Instruct | Phi-3 Medium 128K Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.90 | $1.00 | Llama 3.1 405B Instruct |
| Output (per 1M tokens) | $0.90 | $1.00 | Llama 3.1 405B Instruct |
| Cache Read (per 1M) | $0.45 | N/A | Llama 3.1 405B Instruct |
Using a 3:1 input/output ratio, Llama 3.1 405B Instruct is 10% cheaper overall.
Llama 3.1 405B Instruct Providers
No provider data available
Phi-3 Medium 128K Instruct Providers
No provider data available
Benchmark Comparison
9
Benchmarks Compared
2
Llama 3.1 405B Instruct Wins
1
Phi-3 Medium 128K Instruct Wins
Benchmark Scores
| Benchmark | Llama 3.1 405B Instruct | Phi-3 Medium 128K Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 17.4 | 32.0 | |
Coding Index Code generation & understanding | 14.5 | - | - |
Math Index Mathematical reasoning | 3.0 | - | - |
MMLU Pro Academic knowledge | 73.2 | 41.2 | |
GPQA Graduate-level science | 51.5 | 11.5 | |
LiveCodeBench Competitive programming | 30.5 | - | - |
Aider Real-world code editing | 66.2 | - | - |
AIME Competition math | 21.3 | - | - |
BBH Big-Bench Hard | - | 48.5 | - |
Llama 3.1 405B Instruct significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Llama 3.1 405B Instruct
Other models
Context & Performance
Context Window
Llama 3.1 405B Instruct
131,000
tokens
Phi-3 Medium 128K Instruct
128,000
tokens
Llama 3.1 405B Instruct has a 2% larger context window.
Speed Performance
| Metric | Llama 3.1 405B Instruct | Phi-3 Medium 128K Instruct | Winner |
|---|---|---|---|
| Tokens/second | 33.7 tok/s | N/A | |
| Time to First Token | 0.71s | N/A |
Capabilities
Feature Comparison
| Feature | Llama 3.1 405B Instruct | Phi-3 Medium 128K Instruct |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Llama 3.1 405B Instruct | Phi-3 Medium 128K Instruct |
|---|---|---|
| License | Open Source | Open Source |
| Author | Meta-llama | Microsoft |
| Released | Jul 2024 | Unknown |
Llama 3.1 405B Instruct Modalities
Input
text
Output
text
Phi-3 Medium 128K Instruct Modalities
Input
Output