Key Takeaways
Llama 3.3 70B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Better at coding
- Better at math
WizardLM-2 8x22B wins:
- Higher intelligence benchmark
Price Advantage
Llama 3.3 70B Instruct
Benchmark Advantage
Llama 3.3 70B Instruct
Context Window
Llama 3.3 70B Instruct
Speed
Llama 3.3 70B Instruct
Pricing Comparison
Price Comparison
| Metric | Llama 3.3 70B Instruct | WizardLM-2 8x22B | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.10 | $0.62 | Llama 3.3 70B Instruct |
| Output (per 1M tokens) | $0.32 | $0.62 | Llama 3.3 70B Instruct |
| Cache Read (per 1M) | $0.13 | N/A | Llama 3.3 70B Instruct |
Using a 3:1 input/output ratio, Llama 3.3 70B Instruct is 75% cheaper overall.
Llama 3.3 70B Instruct Providers
No provider data available
WizardLM-2 8x22B Providers
No provider data available
Benchmark Comparison
9
Benchmarks Compared
3
Llama 3.3 70B Instruct Wins
1
WizardLM-2 8x22B Wins
Benchmark Scores
| Benchmark | Llama 3.3 70B Instruct | WizardLM-2 8x22B | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 14.5 | 33.1 | |
Coding Index Code generation & understanding | 10.7 | - | - |
Math Index Mathematical reasoning | 7.7 | - | - |
MMLU Pro Academic knowledge | 71.3 | 40.0 | |
GPQA Graduate-level science | 49.8 | 17.6 | |
LiveCodeBench Competitive programming | 28.8 | - | - |
Aider Real-world code editing | 59.4 | 44.4 | |
AIME Competition math | 30.0 | - | - |
BBH Big-Bench Hard | - | 48.6 | - |
Llama 3.3 70B Instruct significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Llama 3.3 70B Instruct
Other models
Context & Performance
Context Window
Llama 3.3 70B Instruct
131,072
tokens
WizardLM-2 8x22B
65,535
tokens
Llama 3.3 70B Instruct has a 50% larger context window.
Speed Performance
| Metric | Llama 3.3 70B Instruct | WizardLM-2 8x22B | Winner |
|---|---|---|---|
| Tokens/second | 99.5 tok/s | N/A | |
| Time to First Token | 0.54s | N/A |
Capabilities
Feature Comparison
| Feature | Llama 3.3 70B Instruct | WizardLM-2 8x22B |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Llama 3.3 70B Instruct | WizardLM-2 8x22B |
|---|---|---|
| License | Open Source | Open Source |
| Author | Meta-llama | Microsoft |
| Released | Dec 2024 | Apr 2024 |
Llama 3.3 70B Instruct Modalities
Input
text
Output
text
WizardLM-2 8x22B Modalities
Input
text
Output
text