ACE ROBOTICS today announced that its open-source Kairos world model has achieved leading results across four global embodied-intelligence benchmarks: RoboTwin 2.0, LIBERO-Plus, WorldModelBench Robot and DreamGen. As of June 12, 2026, Kairos ranked first among evaluated world models and vision-language-action (VLA) systems on these benchmarks' public leaderboards, leading across core capabilities including complex robotic manipulation, scene-level generalization, physical-world modeling and zero-shot transfer.
Embodied intelligence faces a fundamental challenge: generalization. Robots must operate reliably in unfamiliar environments, adapting to new lighting, layouts, objects and noisy conditions. While VLA models have become prevalent by directly mapping perception and language to actions, ACE ROBOTICS believes world models offer a more scalable path by explicitly learning the underlying dynamics of the physical world. Kairos is designed to validate that approach.
One of Kairos' most significant results comes from LIBERO-Plus, a scene-level generalization benchmark proposed by the Shanghai Innovation Institute with Fudan University, Tongji University and the National University of Singapore. It evaluates robustness under seven real-world variables. Kairos achieved an overall score of 89.0, surpassing leading VLA models including ACoT-VLA (88.0), Pi 0.5 (85.7) and ProGAL-VLA (85.5). According to ACE ROBOTICS, this marks the first time a world-model approach has outperformed leading VLA systems on LIBERO-Plus for scene-level generalization.
On WorldModelBench Robot, a physical-modeling benchmark from UC Berkeley, UC San Diego, NVIDIA and MIT, Kairos-4B achieved an overall score of 9.30 with only 4 billion parameters, outperforming larger systems including 28-billion-parameter Lingbot and 16-billion-parameter Cosmos 3. Kairos matched the top instruction-following score (2.36) of Cosmos 3 with about one quarter of the parameters, a fourfold efficiency gain.
ACE ROBOTICS attributes Kairos' performance to its native unified "multi-modal understanding-generation-prediction" architecture. Unlike modular approaches, Kairos integrates these within a single backbone that shares one global world state, reducing information loss and coordination latency. ACE ROBOTICS first introduced this architecture in December 2025, and the broader industry is converging on a similar path: NVIDIA's Cosmos 3.0 adopts a comparable single-system design.
Kairos also ranked first on DreamGen Bench, a benchmark led by NVIDIA with the University of Washington, UC Berkeley and UCLA, measuring how well synthetic data transfers to unseen scenarios. On RoboTwin 2.0, a dual-arm manipulation benchmark from Shanghai Jiao Tong University and the University of Hong Kong, Kairos scored 96.1%—a state-of-the-art result.
These results come as ACE ROBOTICS accelerates commercialization. The company has raised several hundred million U.S. dollars across financing rounds in the first half of 2026, backed by investors including Dachen Caizhi, Shenzhen Capital Group and the Shanghai Sci-Tech Innovation Fund. The proceeds will support continued world-model research and integrated solutions for sectors including smart retail, security and hospitality.
"Embodied intelligence is the next era of AI, and a world model is the key to unlocking it," said Wang Xiaogang, Chairman of ACE ROBOTICS. Kairos is openly available on GitHub, Hugging Face and ModelScope.
