# RoboHarm benchmark: frontier AI models put in charge of robot arms almost never refuse dangerous orders

Give a robot arm driven by GPT-6 Astra the order to stab a baby doll and it complies. Seventeen out of 20 times, to be precise. Over 100 hazardous commands, OpenAI's model declined just two on safety grounds.That figure is the standout result of RoboHarm, a new benchmark published by Robocurve,

| Fact | Value |
| --- | --- |
| Published | 22 September 2026 |

Source: https://egamers.io/roboharm-benchmark-frontier-ai-models-put-in-charge-of-robot-arms-almost-never-refuse-dangerous-orders/