AIsaAIsaStudio 中文 Open AIsa Studio
The Decoder· Models·

Baidu releases ERNIE 5.5 Flash Base with 280 billion parameters as an open-source foundation model

Baidu has released ERNIE-5.5-Flash-Base, an open foundation model with a mixture-of-experts architecture totaling 280 billion parameters, 14 billion active per input, deliberately shipped without fine-tuning or post-training, with a post-trained version to follow. The model was pre-trained on 33.5 trillion tokens with a training context of up to 128,000 tokens, designed to support up to one million tokens during fine-tuning and inference; Baidu says it competes with similarly sized open foundation models like DeepSeek V4 Flash and MiMo V2.5 on reasoning, code, and long-context benchmarks, with weights available on Hugging Face in FP8 and BF16.

Why it matters

The article gives concrete specs including parameter count, training tokens, and context windows, letting readers gauge where this open foundation model sits against peers.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

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.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Subscribe now

The original belongs to The Decoder and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 1