GPT-6.2 Astra Raises Ember-0 Manipulation Success Rate to 41.2%
XDOF reportedly measured GPT-6.2 Astra at a 41.2% aggregate success rate across 16 dual-arm manipulation tasks in the Ember-0 benchmark, up from 19.6% for GPT-6 Astra. The model reportedly completed knot-tying and T-shirt unfolding, while average prediction latency fell from 15 seconds to 10.1 seconds. The claim that these were the first successful completions of deformable-object tasks remains unverified beyond XDOF's results.
The results suggest a substantial gain in general-purpose models' physical manipulation abilities, although the remaining latency and lack of independent verification limit the practical conclusion.
GPT-6.2 Astra再次暴击具身模型:16项任务成功率较GPT-6 Astra翻倍 – 量子位
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
GPT-6.2 Astra再次暴击具身模型:16项任务成功率较GPT-6 Astra翻倍

还实现可变形物体操控全球首通