AGIBOT holds World Challenge 2026 to see how AI models perform on real tasks
The AGIBOT World Challenge 2026 brought together 526 research and enterprise teams to compete in two embodied AI tracks, testing and debugging robots working on different tasks.

In a significant step towards advancing embodied AI, AGIBOT Innovation Technology Co. recently hosted the AGIBOT World Challenge 2026 in Vienna, alongside ICRA 2026. The competition drew 526 research and enterprise teams from 27 countries, who came together to compete across two embodied AI tracks: 'Reasoning to Action' and 'World Model.' This event marked a key shift in how embodied AI is evaluated, moving beyond simulation scores to closed-loop testing on real robots, real tasks, and standardized benchmarks.
The challenge adopted a benchmark-driven format that combined online automated evaluation with an offline real-robot final. The competition used AGIBOT's EWMBench and Genie Sim Benchmark, providing a consistent framework that enabled automated testing, standardized metrics, and reproducible results. During the offline final, finalist teams completed tasks using the AGIBOT G2 humanoid robot.
The company emphasized that incorporating real-robot validation into the evaluation process placed robot stability, real-world adaptability, and long-horizon task reliability at the center of the scoring system. The competition saw participation from leading institutions and companies, including the Chinese Academy of Sciences, Tsinghua University, the University of Science and Technology of China, the University of California San Diego, Russia's Sber Robotics Center, Alibaba, Amap, and vivo. More than 100 teams surpassed the official baseline.
The two tracks reflected the broader evolution of embodied AI from task execution toward understanding, prediction, and decision-making. In the final ranking, PrismBot from vivo won the championship with 43.47 points, followed by Shanghai RoboParty's RP-VLA with 35.66 points and Russia's GreenVLA with 33.19 points. Alongside the competition, AGIBOT and Dexmal launched a supermarket benchmark track focused on end-to-end decision-making and whole-body control.
AGIBOT's goal is to contribute to a more practical and reproducible evaluation framework for embodied AI. Beyond the competition, AGIBOT opened a full-stack toolchain covering real-world data, simulation evaluation, and real-robot testing. The toolchain included the AGIBOT WORLD open-source dataset, Genie Sim 3.0, and the AGIBOT G2 robot platform.
AGIBOT plans to integrate the technical and ecosystem resources developed through the competition with its ongoing benchmark development and open-source efforts.
Source: The Robot Report