AITOPAI热报
Models

百度开源 ERNIE 5.5 Flash Base：280B 参数 MoE 模型

shao__meng@shao__meng
Post
View the post
Why we picked it

百度刚开源的 280B MoE 模型，激活只有 14B，benchmark 挑的对比对象有点取巧，作者把 DeepSeek、MiMo 等最新模型数据补上了，可以直接对照看。

百度开源了 ERNIE 5.5 Flash Base，采用 MoE 架构，总参数 280B、激活参数 14B。官方 benchmark 选择的是同参数量级模型对比，而非各家最新旗舰。作者额外列出了 DeepSeek-V4.1-Flash-1017、Hy4、MiMo-V2.6-Flash 等最新模型，供读者自行对照参考。

Original · shao__meng

没忍住还是想发这张图 😂 meng shao @shao__meng 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 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 62 ⚡

#ERNIE 5.5#百度#开源模型#MoE#DeepSeek

Keep reading

Recent stories with the same tag or section
ModelsUS vs ChinaMulti-sourceSelected18:56
Tencent Hunyuan Hy4 scores 35 on Intelligence Index v5

Hy4 achieves parity with Grok 4.7 at one-tenth the cost, with a Cost per Intelligence Index Task of US$0.78 versus far pricier Western peers. The main caveat is an 89% hallucination rate on AA-Omniscience v1.1 against Kimi K3.1 Pro's 37%, so agentic coding is the safer use case than knowledge retrieval. Teams benchmarking China-based models against Claude, Grok or Qwen options should weigh that trade-off directly.

#Tencent Hunyuan#Hy4#Artificial Analysis#reasoning models
Event
Hunyuan@TXhunyuan8 sourcesSource