Google 论文：最强 AI 智能体在真实工程任务上仅得 50.6%
Google 做了个 PLE 基准，85 个真实工程活，Claude Opus 5.5 才考 50.6 分，做工程智能体的可以看看它栽在哪。
Google 团队发布了 PLE 基准，包含 85 个由在职工程师撰写或审核的电气、土木、结构与机械任务，每个任务需读取约 61 个项目文件并输出进度表、报告或 2D/3D 图纸。在 14 个被测模型中，Claude Opus 5.5 搭配 Claude Code 以 50.6% 拿下第一，单任务消耗 2700 万 token、耗时 63 分钟。该模型在设计类任务上满足 91% 的约束条件，但仅有 41.3% 满足全部硬性约束，常见失败原因是漏掉安全或可行性规则。论文建议构建工程智能体时先用硬性安全与规范校验把关设计输出。
New Google paper finds that the best AI agent scores only 50.6% on physical engineering jobs, often by missing a hard safety or feasibility rule.
Engineering benchmarks for LLMs mostly test textbook questions or toy problems that top agents already handle well. Real engineers work from piles of PDFs, spreadsheets, and CAD files and must issue designs that meet code and stay cheap.
They built PLE, 85 electrical, civil, structural, and mechanical jobs written or checked by practising engineers. Agents must read about 61 project files per task and deliver schedules, reports, or 2D and 3D drawings.
Claude Opus 5.5 in Claude Code topped 14 models at 50.6%, using 27M tokens and 63 minutes per task. On design tasks its outputs met 91% of constraints, but only 41.3% met every hard constraint.
If you build engineering agents, gate every design on hard safety and code limits, and spend effort on model choice before tuning the agent scaffold.
