# Baidu open-sources ERNIE 5.5 Flash Base, a 280B MoE model

> Original title: 百度开源发布了 ERNIE 5.5 Flash Base

- Source: meng shao
- Published: 2026-11-05T09:46:04.000Z
- Bad Influence: https://badinfluence.news/items/b73itg8bmfsxf0lu7jbdfz85v
- Original: https://x.com/shao__meng/status/2118278665369006294

## Summary

Baidu has open-sourced ERNIE 5.5 Flash Base, a mixture-of-experts model with 280B total parameters and 14B active per token. The company says it matches state-of-the-art models at its size, and a full ERNIE 5.5 Flash is coming. The post compares it against DeepSeek-V4-Flash-Base, Hy3-preview-Base and MiMo-V2.5-Base, using DeepSeek-V4.1-Flash-1017, Hy4 and MiMo-V2.6-Flash as the latest models from each vendor.

## Post

百度开源发布了 ERNIE 5.5 Flash Base

一个 MoE 架构模型，280B/A14B 参数

不过 benchmark 对比的怎么都不是各家最新模型呢？原来是因为想对比同参数量级，好吧，还是把各家最新模型列出来，方便大家参考。

DeepSeek-V4-Flash-Base -> V4.1-Flash-1017
Hy3-preview-Base -> Hy4
MiMo-V2.5-Base -> MiMo-V2.6-Flash

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWWjNpLaQAA4Ubb.jpg&mode=thumb&exp=1794096000&sig=06cd3ee92457a9dc)

## Quoted post @BaiduResearch

> ERNIE 5.5 Flash Base is now open source — a 280B-parameter model with 14B active per token, and it already matches SOTA at its size!
> And this is just the start — the full ERNIE 5.5 Flash is on its way. 👀

https://x.com/BaiduResearch/status/2118249227939967424