Event ·Single source

腾讯混元发布WebCraftBench评估AI生成网站

腾讯混元团队推出WebCraftBench评估系统，通过智能体实际使用生成的网站进行测试。该系统在197个人类验证的样本对上，达到85.3%的人类偏好匹配率。WebCraftBench采用覆盖率引导的探索方法，发现未被测试的功能区域，并评估美学、可用性和原始请求完成度。

Current read

腾讯混元这个新工具能真实测试AI生成的网站，比人工评估更高效准确。

2 sources63° AI heatLast updated 2026/9/22 08:53:39

Evidence

2 sources

Primary sourceHunyuan

2026/9/22 08:53:39View source

Related source 1lmarena.ai

2026/9/23 20:30:27View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story