ERNIE 4.5 VL 424B
Baidu's large vision-language MoE model — 424B total, 47B active. State-of-the-art Chinese multimodal model for complex visual understanding and analysis.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Providers
Compare with
Frequently Asked Questions about ERNIE 4.5 VL 424B▼
Who created ERNIE 4.5 VL 424B?
▼
ERNIE 4.5 VL 424B was created by Baidu.
Is ERNIE 4.5 VL 424B a reasoning model?
▼
No, ERNIE 4.5 VL 424B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does ERNIE 4.5 VL 424B support image or vision input?
▼
Yes, ERNIE 4.5 VL 424B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does ERNIE 4.5 VL 424B support audio?
▼
No, ERNIE 4.5 VL 424B does not support audio input.
What is the context window of ERNIE 4.5 VL 424B?
▼
ERNIE 4.5 VL 424B has a context window of 123K tokens, meaning it can process approximately 92,250 words of context at once.
Is ERNIE 4.5 VL 424B open source?
▼
ERNIE 4.5 VL 424B is a proprietary model developed by Baidu. The model weights and training data are not publicly available.
What is ERNIE 4.5 VL 424B good at?
▼
Based on benchmark data, ERNIE 4.5 VL 424B excels at: visual analysis and image understanding. It is Baidu's capable model suitable for a wide range of tasks.
Where can I use ERNIE 4.5 VL 424B?
▼
You can chat with ERNIE 4.5 VL 424B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access ERNIE 4.5 VL 424B through Baidu's own API or platform.