Key Takeaways
Gemini 3 Pro Preview wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Supports vision
- Has reasoning mode
Qwen2.5 72B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
Price Advantage
Qwen2.5 72B Instruct
Benchmark Advantage
Gemini 3 Pro Preview
Context Window
Gemini 3 Pro Preview
Speed
Gemini 3 Pro Preview
Pricing Comparison
Price Comparison
| Metric | Gemini 3 Pro Preview | Qwen2.5 72B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $2.00 | $0.12 | Qwen2.5 72B Instruct |
| Output (per 1M tokens) | $12.00 | $0.39 | Qwen2.5 72B Instruct |
| Cache Read (per 1M) | $200000.00 | N/A | Gemini 3 Pro Preview |
| Cache Write (per 1M) | $375000.00 | N/A | Gemini 3 Pro Preview |
Using a 3:1 input/output ratio, Qwen2.5 72B Instruct is 96% cheaper overall.
Gemini 3 Pro Preview Providers
Google AI Studio $2.00 (Cheapest)
Google $2.00 (Cheapest)
Qwen2.5 72B Instruct Providers
DeepInfra $0.12 (Cheapest)
Chutes $0.30
Novita $0.38
Hyperbolic $0.40
Benchmark Comparison
8
Benchmarks Compared
6
Gemini 3 Pro Preview Wins
0
Qwen2.5 72B Instruct Wins
Benchmark Scores
| Benchmark | Gemini 3 Pro Preview | Qwen2.5 72B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 48.4 | 15.6 | |
Coding Index Code generation & understanding | 46.5 | 11.9 | |
Math Index Mathematical reasoning | 95.7 | 14.0 | |
MMLU Pro Academic knowledge | 89.8 | 72.0 | |
GPQA Graduate-level science | 90.8 | 49.1 | |
LiveCodeBench Competitive programming | 91.7 | 27.6 | |
Aider Real-world code editing | - | 65.4 | - |
AIME Competition math | - | 16.0 | - |
Gemini 3 Pro Preview significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Gemini 3 Pro Preview
Other models
Context & Performance
Context Window
Gemini 3 Pro Preview
1,048,576
tokens
Max output: 65,536 tokens
Qwen2.5 72B Instruct
32,768
tokens
Max output: 16,384 tokens
Gemini 3 Pro Preview has a 97% larger context window.
Speed Performance
| Metric | Gemini 3 Pro Preview | Qwen2.5 72B Instruct | Winner |
|---|---|---|---|
| Tokens/second | 132.8 tok/s | 45.6 tok/s | |
| Time to First Token | 30.65s | 1.11s |
Gemini 3 Pro Preview responds 191% faster on average.
Capabilities
Feature Comparison
| Feature | Gemini 3 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Gemini 3 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| License | Proprietary | Open Source |
| Author | Qwen | |
| Released | Nov 2025 | Sep 2024 |
Gemini 3 Pro Preview Modalities
Input
textimagefileaudiovideo
Output
text
Qwen2.5 72B Instruct Modalities
Input
text
Output
text