Key Takeaways
Gemma 2 27B wins:
- Higher intelligence benchmark
- Supports vision
WizardLM-2 8x22B wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
Price Advantage
WizardLM-2 8x22B
Benchmark Advantage
Gemma 2 27B
Context Window
WizardLM-2 8x22B
Speed
N/A
Pricing Comparison
Price Comparison
| Metric | Gemma 2 27B | WizardLM-2 8x22B | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.65 | $0.62 | WizardLM-2 8x22B |
| Output (per 1M tokens) | $0.65 | $0.62 | WizardLM-2 8x22B |
Using a 3:1 input/output ratio, WizardLM-2 8x22B is 5% cheaper overall.
Gemma 2 27B Providers
No provider data available
WizardLM-2 8x22B Providers
No provider data available
Benchmark Comparison
5
Benchmarks Compared
2
Gemma 2 27B Wins
3
WizardLM-2 8x22B Wins
Benchmark Scores
| Benchmark | Gemma 2 27B | WizardLM-2 8x22B | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 36.2 | 33.1 | |
MMLU Pro Academic knowledge | 38.4 | 40.0 | |
GPQA Graduate-level science | 16.7 | 17.6 | |
Aider Real-world code editing | 36.1 | 44.4 | |
BBH Big-Bench Hard | 49.3 | 48.6 |
WizardLM-2 8x22B wins 3 out of 5 benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Gemma 2 27B
Other models
Context & Performance
Context Window
Gemma 2 27B
8,192
tokens
WizardLM-2 8x22B
65,535
tokens
WizardLM-2 8x22B has a 87% larger context window.
Speed Performance
Speed benchmarks not available for these models
Capabilities
Feature Comparison
| Feature | Gemma 2 27B | WizardLM-2 8x22B |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Gemma 2 27B | WizardLM-2 8x22B |
|---|---|---|
| License | Open Source | Open Source |
| Author | Microsoft | |
| Released | Jul 2024 | Apr 2024 |
Gemma 2 27B Modalities
Input
text
Output
text
WizardLM-2 8x22B Modalities
Input
text
Output
text