Original post · AI translation
标题：“GenXR-Bench：面向交互式 XR 开发的编码智能体基准测试”
Google、UCLA 和 CMU 的一篇新论文发现，AI 编码工具经常无法构建虚拟现实和混合现实应用，因为它们会弄不清物体在 3D 空间中的位置。
Claude Opus 5 以 50.9% 领先，而在 SDK 功能任务上，没有模型超过 29.2%。在失败的运行中，64.4% 出现了坐标系错误，44.9% 出现了启动时的竞态条件。
XR 应用在 3D 空间中运行，并对头部运动、手部动作和房间感知作出反应。常规编码基准测试使用单元测试或浏览器点击操作，无法检查虚拟按钮是否会跟随你的手掌移动。
他们构建了 GenXR-Bench，其中包含 112 项由专家编写的任务，涵盖 XR 功能开发、错误修复和完整应用构建。其测试会模拟手部和房间输入，与使用真实头显的盲测 XR 专家的判断有 96.5% 的一致率。
如果你使用智能体开发 XR 应用，请用模拟的手部和房间输入来测试结果，因为智能体编写的单元测试经常会漏掉运行时错误。
Original
New Google + UCLA + CMU paper finds that AI coding tools often fail to build virtual and mixed reality apps because they lose track of where things are in 3D space. Claude Opus 5 led at 50.9%, and no model topped 29.2% on SDK feature tasks. Coordinate-frame mistakes appeared in 64.4% of failed runs, and startup race conditions in 44.9%. XR apps run in 3D space and react to head motion, hands, and room sensing. Normal coding benchmarks use unit tests or browser clicks, which cannot check whether a virtual button follows your palm. They built GenXR-Bench, 112 expert-written tasks covering XR feature work, bug fixes, and full app builds. Its tests simulate hands and rooms, and matched blinded XR experts using real headsets 96.5% of the time. If you use agents for XR apps, test the result with simulated hand and room input, since agent-written unit tests often miss runtime bugs.