Baidu Open-Sources 280B-Parameter ERNIE 5.5 Flash Base Foundation Model
Baidu released ERNIE-5.5-Flash-Base on Hugging Face, a mixture-of-experts foundation model with 280B total parameters and 14B active per token, pre-trained on 33.5 trillion tokens with a 128K training context that can extend to one million tokens during fine-tuning and inference. It ships deliberately without fine-tuning or post-training, positioning the raw weights for developer customization, with a post-trained version to follow.
Full Report
Baidu releases ERNIE 5.5 Flash Base with 280 billion parameters as an open-source foundation model
[Matthias Bastian](https://the-decoder.com/author/matthias-bastian/) [View the LinkedIn Profile of Matthias Bastian](https://www.linkedin.com/in/matthias-bastian-128b71b1/) Nov 5, 2026 Baidu's AI development is still alive, but most of the work is on you. The Chinese company has released ERNIE-5.5-Flash-Base, an open foundation model that ships deliberately without fine-tuning or post-training. Developers are expected to decide for themselves where to take the model. A post-trained version is supposed to follow.
ERNIE 5.5 uses a mixture-of-experts architecture with 280 billion parameters, 14 billion of which are active per input. The model was pre-trained on 33.5 trillion tokens with a training context of up to 128,000 tokens, though it's designed to support a context of up to one million tokens during fine-tuning and inference.

Benchmark results for ERNIE 5.5 Flash Base compared to DeepSeek-V4-Flash-Base, Hy3-preview-Base, and MiMo-V2.5-Base, tested with the same evaluation pipeline across the categories Exam, STEM, Reasoning, Knowledge, Code, Multilingual, and Long Context. | Image: Baidu
In benchmarks for reasoning, code, and long-context tasks, the model competes with similarly sized open foundation models like DeepSeek V4 Flash or MiMo V2.5, according to Baidu. The weights are available on Hugging Face in FP8 and BF16.