Baidu Unveils ERNIE 5.5 Flash Preview and Plans to Release Its Weights
Baidu released the ERNIE 5.5 Flash Preview, a foundation model with 280 billion total parameters, 14 billion active parameters per token, a 1 million-token context window, and a reported generation speed above 200 tokens per second. Arena reported a score of 1668 on Code Arena: WebDev, above DeepSeek-V4.1-Flash at 1664 and Kimi K3 at 1658, and close to Qwen3.8-Max at 1670. Baidu said the model weights would be released under Apache 2.0 by November 25.
Baidu presented ERNIE 5.5 Flash Preview as the latest open-weight foundation model in the ERNIE family, with a 1 million-token context window, reported speeds above 200 tokens per second, and planned Apache 2.0 weight availability.
Ernie 5.5 Flash Preview by @Baidu_Inc is trending towards becoming the #2 open model on the Code Arena: WebDev, at 1668 pts. The weights will be open-sourced under Apache 2.0 soon.
Its score puts it just above: - DeepSeek-V4.1-Flash (Max) at 1664 - Kimi K3 (Max) at 1658
and on par with: - Qwen3.8-Max at 1670 Congrats to the @Baidu_Inc team on this release!

@Baidu_Inc: ERNIE 5.5 Flash Preview just landed! 🔥 Built on a new architecture designed for efficient inference, the latest open-weight foundation model in the ERNIE family delivers stronger performance in coding, 3D modeling, knowledge work and content creation. It keeps decoding fast while posting competitive scores on Terminal-Bench, AutomationBench, and other benchmarks. Here's the rundown: - 280B total parameters, 14B active per token - 1M-token context window - Generation speed above 200 tokens/sec Model weights will be released by November 25. https://x.com/Baidu_Inc/status/2120391732248637734
#Baidu#ERNIE 5.5 Flash Preview#DeepSeek-V4.1-Flash#Kimi K3#Qwen3.8-Max