AITOPAI热报
Models

Claude Opus 5.5 控制机械臂后难以判断任务何时结束

官方账号Artificial Analysis@ArtificialAnlys
Post
View the post
Why we picked it

Claude Opus 5.5 控机械臂放鳄鱼，23分钟做完后还多推了22分钟，活儿白干，这个实验挺好笑也挺有启发。

Artificial Analysis 测试了语言模型控制机械臂把玩具鳄鱼放进容器的任务。Claude Opus 5.5 用 23 分钟完成放置，并正确报告任务已完成。但之后它又花 22 分钟反复推拉鳄鱼，最终位置与刚完成时几乎相同。这说明模型在实际操作中难以判断何时停止。

Original · Artificial Analysis

Knowing when to stop is hard for language models controlling a robot arm

➤ Claude Opus 5.5 completed the task in 23 minutes, and said so: "The crocodile looks fully inside now"

➤ It then spent 22 minutes pushing the crocodile back and forth, only to finish almost exactly where it was before

#Claude Opus 5.5#Artificial Analysis#机器人#具身智能

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected09:47
Artificial Analysis Updates Six Capability Indexes to v2.0

The heavier weighting on Non-Hallucination and Agentic Tool Use signals which failure modes actually matter for professional work, and leaderboard positions may shift for models evaluated under the older v1 methodology. Hiring teams and enterprises selecting models for legal, finance or medical workflows can use the six indexes to match models to specific occupations rather than relying on a single aggregate score. Chinese labs' strong open-weight showings from Moonshot, MiniMax and DeepSeek also give cost-sensitive buyers credible alternatives to frontier closed models.

#Artificial Analysis#Claude Opus 5.5#Kimi K3.1 Pro#DeepSeek V4.1
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource