On March 26, the first industry standard in the field of Embodied AI was officially released. Co-drafted by the China Academy of Information and Communications Technology (CAICT) and over 40 collaborating organizations, this standard aims to establish a unified benchmarking framework for the field of Embodied AI, propelling the evaluation of Embodied AI into a new phase of standardization. Focusing on key foundational technologies of artificial intelligence and benchmarking methods for Embodied AI, the standard clarifies the system framework and capability requirements and will be officially implemented on June 1, 2026. The standard specifies benchmarking frameworks, methods, and metrics for both simulated and real-world environments. Its evaluation system supports multiple capability tests, covering four testing methods. During its development, a supporting test task library, testing tools, and a standardized testing environment were concurrently established. Currently, a test task library with over 10,000 entries covering 300 task types has been developed, along with relevant testing tools.