Back to News

Baidu unveils ERNIE 5.5 Flash Preview, 280B-parameter MoE coding model, plans open source

#baidu#ernie#moe#coding

Baidu unveiled ERNIE 5.5 Flash Preview at its World Conference, a 280B-parameter MoE model with 14B active parameters, 1M-token context, and over 200 tokens per second generation speed. The model focuses on coding, demonstrating capabilities in generating animations and games via code, and is slated for open-sourcing. It shows competitive performance against flagship models like Claude Opus 5.5 and GPT-6.1 Sol on Terminal-Bench and AutomationBench.

Coverage timeline

  1. 量子位量子位
    纯代码造《后室》，116秒切20种画风！文心新模型玩嗨了

    纯代码造《后室》，116秒切20种画风！文心新模型玩嗨了 一水 2026-11-11 20:43:54 来源： 量子位 模型即将开源 一水 发自 凹非寺 量子位 | 公众号QbitAI 刚刚，百度发了个新模型，X上的网友们一看Demo直接坐不住了。 百度这是要支棱起来了？？ 都在喊「鹈鹕骑自行车」已经老套过时了，可这样婶儿的版本你见过吗？ 视频地址：https://mp.weixin.qq.com/s/Rj-T8unLFnHUk6R89rt02Q △概念设计来自Bilibili创作者@近步抱告_ 一只鹈鹕骑着自行车，从公元前4000年的撒哈拉岩画，一路闯进大模型时代的代码编辑器。 116秒，20种艺术风格，全程靠Python代码编排动画。 只能说，鹈鹕还是那只鹈鹕，但玩法已经不是一个次元了。。。 就这还只是开胃菜。 刚做完动画，背后的模型 转头又扎进虚幻引擎UE5.8，连续干了11小时，搓出一款东方武侠游戏《云岫行》 。 视频地址：https://mp.weixin.qq.com/s/Rj-T8unLFnHUk6R89rt02Q 张家界石峰、崖顶古寺、人物动作、游戏逻辑……居然全给安排上了。 不是哥们，前脚用代码拍动画，后脚又用代码造游戏，百度这次到底憋了个什么大招？？ 答案揭晓： 文心5.5 Flash Preview （ERNIE 5.5 Flash Preview） 。 就在百度世界大会召开前一天，这款新模型正式亮相，并宣布即将开源。 总参数2800亿，单次推理仅激活140亿参数，支持百万Token上下文，生成速度超过每秒200Token。 而这次，文心重点点亮的技能树只有两个字： 编程。 注意，这里说的编程，早就不止写网页、补代码了，游戏开发、3D建模、视频编排这些需要连续调用工具、反复测试修改的复杂任务，模型也能直接上手干。 目前在Terminal-Bench、AutomationBench等编程与Agent评测中，文心5.5 Flash Preview已经展现出与Claude Opus 5.5、GPT-6.1 Sol等旗舰模型同台竞争的实力。 气氛都烘托到这里了，那就「是骡子是马拉出来遛遛」。 3D、游戏、网页……文心5.5 Flash Preview，接招吧。（doge） 实测文心5.5 Flash Preview 目前网页端和API都能体验这款模型。

Related stories

  • Baidu open-sources ERNIE 5.5 Flash Base, 280B MoE model with 14B active parameters

    On November 5, Baidu open-sourced ERNIE 5.5 Flash Base, a sparse MoE language model with 280B total parameters and 14B active per token, pretrained on 33.5T tokens with up to 128K training context and 1M-token context for fine-tuning and inference. The company claims SOTA results among same-size models on benchmarks covering knowledge, reasoning, math, code, multilingual, and long-context tasks, surpassing DeepSeek-V4-Flash-Base, Hy3-preview-Base, and MiMo-V2.5-Base. The release includes weights on Hugging Face and ecosystem support with vLLM and SGLang.

    3 reports · 2 sources

  • Baidu Wenxin Discloses ERNIE Evolve RSI System, Used in Wenxin 5.5 Flash Inference Optimization

    On November 9, 2026, Baidu Wenxin disclosed its recursive self-improvement (RSI) progress, unveiling the ERNIE Evolve auto-research system used in developing the upcoming Wenxin 5.5 Flash. ERNIE Evolve achieved state-of-the-art results on three benchmarks across NanoChat AutoResearch and NanoGPT Speedrun tasks, and has been applied to optimize inference for Kunlunxin P800, including low-latency performance, deterministic throughput, and decoding speed. The system employs a dual-loop architecture with multiple agents (Director, Selector, Executor, Evaluator, Reviewer) to autonomously propose research directions, run experiments, and retain only verified improvements.

    2 reports · 2 sources

  • Ant Group open-sources Ling-3.1-flash, a 560B-parameter MoE model with 1M context

    Ant Group's Ling-3.1-flash, a 560B-parameter mixture-of-experts model with 25B active parameters and a 1M-token context window, was released open-source on October 15. The model targets long-horizon complex task execution, using a hybrid linear attention design with KDA layers and Gated MLA to manage computational costs on long sequences.

    1 reports · 1 sources

  • ByteDance releases Seedream 5.5 image model with faster generation, transparent assets

    ByteDance released Seedream 5.5, an image generation model now live in Doubao, Doubao Work, and Jimeng, with API coming to Volcano Ark. The model offers faster generation, improved multi-round editing stability (maintaining pixel-level consistency outside edited regions over 100+ rounds), native RGBA transparent asset generation, and enhanced realism and small-text rendering. API pricing continues the two-part structure (input image + output image) with no text token fees; a 2K square image edit costs about 0.28 yuan, less than half of Seedream 5.0 Pro.

    2 reports · 2 sources

News updates every hour. Subscribe in your RSS reader to get new stories automatically.

Subscribe