Baidu Open-Sources ERNIE 5.5 Flash Base, a 280B-Parameter MoE Architecture
English text is being prepared.
Baidu has open-sourced and released ERNIE 5.5 Flash Base, a MoE architecture model with 280B total parameters and 14B activated per token. Baidu Research claims it has reached SOTA at the same size and teases that the full version of ERNIE 5.5 Flash is coming soon. The reposter points out that its benchmark compares models of the same parameter scale rather than each company's latest versions, and lists DeepSeek-V4-Flash-Base corresponding to V4.1-Flash-1017, Hy3-preview-Base corresponding to Hy4, and MiMo-V2.5-Base corresponding to MiMo-V2.6-Flash for reference.
Why read this
AI score 67
Baidu has open-sourced a 280B/A14B MoE model; the author added comparisons with the latest versions of various companies at the same parameter scale, to help judge where this positioning actually stands.
Topics
View original postERNIE 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. 👀
View original
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. 👀
Body
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