961 次浏览 · 12 赞 · 1 转发 （收录时）
腾讯混元分享 OpenDesign 的设计基准测试
- 谁
- OpenDesignDevs
- 引文
We tested 23 models on real-world design tasks based on user requests.
发生了什么
设计基准测试 👇 https://twitter.com/OpenDesignDevs/status/2118630682452996463 @OpenDesignDevs 表示，@TencentHunyuan 的 Hy4 在其设计基准测试中的得分比 GPT-6.1 Sol 低 0.1 分，预估成本低 41%。该测试基于用户请求，对 23 个模型进行了真实设计任务测试；Hy4 排名第 4，现已登陆 OpenDesign。
接下来读什么
查看这件事的完整进展Hy4 Ranks Fourth in OpenDesign’s Design Benchmark正文 · 原文（语言尚未确认）
Design Benchmark 👇 https://twitter.com/OpenDesignDevs/status/2118630682452996463
Hy4 by @TencentHunyuan scores just 0.1 points behind GPT-6.1 Sol in our design benchmark, at 41% lower estimated cost. We tested 23 models on real-world design tasks based on user requests. Hy4 ranks #4. Now on OpenDesign. Full results ↘️在 X 查看被引用的帖子
这件事到目前为止
OpenDesignDevs ranked Tencent Hunyuan’s Hy4 fourth among 23 models in its design benchmark, and Hy4 is now available on OpenDesign. The benchmark tested models on real-world design tasks based on user requests. OpenDesignDevs said Hy4 scored 0.1 points behind GPT-6.1 Sol at an estimated cost 41% lower.
每天一封，跟上 AI 的重要变化
模型发布、价格变化、算力进展，附原始来源。免费，确认后开始发送，随时一键退订。 看一份往期日报 · 2026-11-06