Key Takeaways
Llama 3.1 405B Instruct wins:
- Higher intelligence benchmark
- Better at coding
Llama 3.2 3B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Better at math
Price Advantage
Llama 3.2 3B Instruct
Benchmark Advantage
Llama 3.1 405B Instruct
Context Window
Llama 3.2 3B Instruct
Speed
Llama 3.2 3B Instruct
Pricing Comparison
Price Comparison
| Metric | Llama 3.1 405B Instruct | Llama 3.2 3B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $4.00 | $0.02 | Llama 3.2 3B Instruct |
| Output (per 1M tokens) | $4.00 | $0.02 | Llama 3.2 3B Instruct |
Using a 3:1 input/output ratio, Llama 3.2 3B Instruct is 100% cheaper overall.
Llama 3.1 405B Instruct Providers
Hyperbolic $4.00 (Cheapest)
Google $5.00
Llama 3.2 3B Instruct Providers
DeepInfra $0.02 (Cheapest)
Novita $0.03
Cloudflare $0.05
Together $0.06
Hyperbolic $0.10
Benchmark Comparison
8
Benchmarks Compared
5
Llama 3.1 405B Instruct Wins
0
Llama 3.2 3B Instruct Wins
Benchmark Scores
| Benchmark | Llama 3.1 405B Instruct | Llama 3.2 3B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 14.2 | 9.7 | |
Coding Index Code generation & understanding | 14.5 | - | - |
Math Index Mathematical reasoning | 3.0 | 3.3 | - |
MMLU Pro Academic knowledge | 73.2 | 34.7 | |
GPQA Graduate-level science | 51.5 | 25.5 | |
LiveCodeBench Competitive programming | 30.5 | 8.3 | |
Aider Real-world code editing | 66.2 | - | - |
AIME Competition math | 21.3 | 6.7 |
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
Llama 3.2 3B Instruct
131,072
tokens
Max output: 16,384 tokens
Llama 3.2 3B Instruct has a 0% larger context window.
Speed Performance
| Metric | Llama 3.1 405B Instruct | Llama 3.2 3B Instruct | Winner |
|---|---|---|---|
| Tokens/second | 25.2 tok/s | 44.1 tok/s | |
| Time to First Token | 0.79s | 0.43s |
Llama 3.2 3B Instruct responds 75% faster on average.
Capabilities
Feature Comparison
| Feature | Llama 3.1 405B Instruct | Llama 3.2 3B 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 | Llama 3.2 3B Instruct |
|---|---|---|
| License | Open Source | Open Source |
| Author | Meta-llama | Meta-llama |
| Released | Jul 2024 | Sep 2024 |
Llama 3.1 405B Instruct Modalities
Input
text
Output
text
Llama 3.2 3B Instruct Modalities
Input
text
Output
text