Key Takeaways
ERNIE 4.5 VL 28B A3B wins:
- Supports vision
Step 3.5 Flash wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
Price Advantage
Step 3.5 Flash
Benchmark Advantage
Step 3.5 Flash
Context Window
Step 3.5 Flash
Speed
Step 3.5 Flash
Pricing Comparison
Benchmark Comparison
Context & Performance
Capabilities
Feature Comparison
| Feature | ERNIE 4.5 VL 28B A3B | Step 3.5 Flash |
|---|---|---|
Vision (Image Input) | ||
Tool/Function Calls | ||
Reasoning Mode | ||
Audio Input | ||
Audio Output | ||
PDF Input | ||
Prompt Caching | ||
Web Search |
License & Release
| Property | ERNIE 4.5 VL 28B A3B | Step 3.5 Flash |
|---|---|---|
| License | Open Source | Open Source |
| Author | Baidu | Stepfun-ai |
| Released | Aug 2025 | Jan 2026 |
ERNIE 4.5 VL 28B A3B Modalities
Input
textimage
Output
text
Step 3.5 Flash Modalities
Input
text
Output
text
