Key Takeaways
Gemma 2 27B wins:
- Cheaper input tokens
- Cheaper output tokens
- Higher intelligence benchmark
- Supports vision
Phi-3 Medium 128K Instruct wins:
- Larger context window
Price Advantage
Gemma 2 27B
Benchmark Advantage
Gemma 2 27B
Context Window
Phi-3 Medium 128K Instruct
Speed
N/A
Pricing Comparison
Price Comparison
| Metric | Gemma 2 27B | Phi-3 Medium 128K Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.65 | $1.00 | Gemma 2 27B |
| Output (per 1M tokens) | $0.65 | $1.00 | Gemma 2 27B |
Using a 3:1 input/output ratio, Gemma 2 27B is 35% cheaper overall.
Gemma 2 27B Providers
No provider data available
Phi-3 Medium 128K Instruct Providers
No provider data available
Benchmark Comparison
5
Benchmarks Compared
3
Gemma 2 27B Wins
1
Phi-3 Medium 128K Instruct Wins
Benchmark Scores
| Benchmark | Gemma 2 27B | Phi-3 Medium 128K Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 36.2 | 32.0 | |
MMLU Pro Academic knowledge | 38.4 | 41.2 | |
GPQA Graduate-level science | 16.7 | 11.5 | |
Aider Real-world code editing | 36.1 | - | - |
BBH Big-Bench Hard | 49.3 | 48.5 |
Gemma 2 27B 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
Phi-3 Medium 128K Instruct
128,000
tokens
Phi-3 Medium 128K Instruct has a 94% larger context window.
Speed Performance
Speed benchmarks not available for these models
Capabilities
Feature Comparison
| Feature | Gemma 2 27B | 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 | Gemma 2 27B | Phi-3 Medium 128K Instruct |
|---|---|---|
| License | Open Source | Open Source |
| Author | Microsoft | |
| Released | Jul 2024 | Unknown |
Gemma 2 27B Modalities
Input
text
Output
text
Phi-3 Medium 128K Instruct Modalities
Input
Output