GPT-6-Astra's Embodied Capabilities Face Major Test
GPT-6-Astra具身能力遭大考！传统基准拿满分，真机频碰壁
A research team from SenseNova and collaborators conducted a comprehensive evaluation of GPT-6-Astra's embodied intelligence capabilities, achieving high scores in simulated benchmarks but facing significant challenges in real-world robot execution. The study highlights issues such as high computational cost, physical interaction accuracy, and task completion reliability in real environments.
The study evaluates GPT-6-Astra's embodied intelligence capabilities through 12 simulated benchmarks and 8 real-world robot platforms, highlighting its high performance in structured tasks but significant limitations in real-world execution, including cost, time, and physical interaction accuracy.
Source: Chinese robotics — Robot learning research · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
87.3%
View original evidence
对于更复杂的灵巧操作，GPT-6-Astra 在 DexJoCo 上取得 87.3% 成功率，在 RoboDojo 上达到 81.9%。
Open source S19Reported success rate
27.6%
View original evidence
这一调整带来的效果立竿见影，以 RoboDojo 基准为例，其上的成功率从标准预算下的 27.6% 提高到 10× 预算下的 81.9%。
Open source S24
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
」 近日，商汤联合大晓机器人、Ropedia、新加坡南洋理工大学和东京大学的研究团队在《Has GPT-6-Astra Achieved Embodied Intelligence?》中，给出了 覆盖 12 项仿真评测、8 个真实机器人平台的系统分析 。
Open source S5
技术报告地址：https://www.sensenova.ai/has-gpt-6-astra-achieved-embodied-intelligence 有意思的是，同一个 GPT-6-Astra，在简单解除限制之后，在多项传统具身评测中交出了满分或接近满分的成绩：其中在长程组合操作评测基准 LIBERO-Long++ 上达到 100%，在考察操作鲁棒性和泛化能力的 LIBERO-Pro 上达到 99.3%，人形机器人基准 SIMPLE 上达到 98.8%，RoboDojo 上也可以达到 81.9%。
Open source S7
除了上文已经提到的 LIBERO-Long++、LIBERO-Pro 和 SIMPLE，在超长程机器人操作基准 LIBERO-Ultra-Long 上为 98.9%。
Open source S18
对于更复杂的灵巧操作，GPT-6-Astra 在 DexJoCo 上取得 87.3% 成功率，在 RoboDojo 上达到 81.9%。
Open source S19
这一调整带来的效果立竿见影，以 RoboDojo 基准为例，其上的成功率从标准预算下的 27.6% 提高到 10× 预算下的 81.9%。
Open source S24
Source：Chinese robotics — Robot learning research · finance.sina.com.cn