![\"motubrain](\"https:\/\/deepinsightai.io\/wp-content\/uploads\/2026\/04\/MotuBrain-Leads-Both-WorldArena-and-RoboTwin2.0-1024x574.webp\" "\\"MotuBrain")
<\/figure>\n\n\n\nOn WorldArena, MotuBrain ranked first with an overall EWM Score of 63.77. From the results, its performance surpasses models like Gaode\u2019s ABot and Jijia\u2019s GigaWorld-1, and it leads across key motion dimensions such as Motion Quality, Flow Score, and Motion Smoothness.<\/p>\n\n\n\n
On RoboTwin2.0, MotuBrain reached 95.8 and 96.1 in Clean and Randomized settings respectively, also ranking first. It is the only model on the leaderboard with an average score above 95 in randomized environments, and in most specific tasks it achieved 100 or close to 100. Compared to models like Gaode ABot, Ant Lingbo LingBot<\/a>, JEPA-VLA, and pi0.5, MotuBrain shows a dominant performance in the RoboTwin benchmark.<\/p>\n\n\n\n It is precisely this \u201cdouble first place\u201d that makes people start paying attention to this unknown model.<\/p>\n\n\n\n A quick search shows that there is still almost no information about MotuBrain online, but there is an X account registered just this month.<\/p>\n\n\n\n This brings to mind the earlier \u201cHuanle Ma\u201d that was later claimed by Alibaba (which also opened an X account afterward).<\/p>\n\n\n\n This mysterious world model\u2014could it also come from some major domestic tech company?<\/p>\n\n\n\n WorldArena and RoboTwin are not the same type of test; they measure two different capabilities.<\/p>\n\n\n\n WorldArena evaluates the world model dimension: whether the model can understand motion laws, whether it can accurately infer and predict physical changes in time series, and whether it has awareness of environmental state changes. This is the ability to predict the world.<\/p>\n\n\n\n RoboTwin, on the other hand, leans toward the action model or policy model dimension\u2014for example, whether the model can execute actions stably across multiple tasks and environments, whether it can generalize to unseen scenarios, and whether it can continuously complete complex operations. This is the ability to act in the world.<\/p>\n\n\n\n Think of it this way. The reason a human driver can drive safely in complex traffic is not just muscle memory, but constant prediction of what will happen in the next second\u2014will the car ahead brake suddenly? Will a pedestrian cross unexpectedly? This synchronization of prediction and action is the underlying logic of human intelligence.<\/p>\n\n\n\n Most existing robotic systems lack exactly this layer. They either are good at understanding the world but don\u2019t know how to act, or they can execute fixed actions but have no prediction of environmental changes. This split leads to robots easily failing once they leave their training scenarios.<\/p>\n\n\n\n Over the past few years, both directions have been explored, but mostly in isolation. Teams working on video generation and world models focus on whether models can realistically simulate the physical world; teams working on robot policy and VLA focus on how to make models execute reliably on specific tasks. There have been few attempts to truly unify the two, and even fewer stable results.<\/p>\n\n\n\n MotuBrain being able to take first place in both types of benchmarks at least verifies one thing at the benchmark level: unifying world prediction and action driving within a single model is a viable path.<\/p>\n\n\n\n On the WorldArena leaderboard, what stands out about MotuBrain is its lead in several dimensions.<\/p>\n\n\n\n Motion Quality ranks first, meaning the actions generated by the model are more realistic, not just visually moving effects.<\/p>\n\n\n\n Flow Score ranks first, indicating a deeper understanding of continuous motion and trajectories, and the ability to stably predict large-scale motion changes\u2014smoothly connecting one moment to the next rather than stitching frame by frame.<\/p>\n\n\n\n Motion Smoothness ranks first, meaning the generated actions better follow real physical laws, without unnatural sudden acceleration, jitter, or direction jumps.<\/p>\n\n\n\n These three dimensions are all directly related to motion. For a future world model meant to serve robots, this is exactly the most critical capability.<\/p>\n\n\n\n On the more task-execution-focused RoboTwin, this advantage is further amplified. Facing 50 tasks and two different environment settings, MotuBrain\u2019s average score reaches 96.0, significantly higher than the second place at 92.3. The gap is almost equal to the difference between second and fifth place.<\/p>\n\n\n\n More importantly, there is stability. Half of the tasks have a 100% success rate, and 90% of tasks exceed 90%. This doesn\u2019t just mean it can get things right\u2014it means it can consistently reproduce results across multiple tasks and under random disturbances.<\/p>\n\n\n\n Taken together, these results point to something closer to a general robot brain: maintaining continuity and consistency at the action level while also having cross-task generalization ability.<\/p>\n\n\n\n At present, there is very little public information about MotuBrain. But judging from the structure of its results across the two leaderboards, it is unlikely to be a traditional video model, nor a purely VLA or policy model. It represents a different kind of reasoning, distinct from the adaptive thinking<\/a> found in top-tier language models, focusing intensely on pure physical intelligence.<\/p>\n\n\n\n Over the past year, exploration around world models and action models has formed several representative paths in the industry.<\/p>\n\n\n\n Some emphasize a unified world model, combining vision, language, video, and action through joint modeling\u2014integrating video models, VLA, world models, and more\u2014to achieve perception, planning, prediction, execution, and cross-task generalization in real environments. A typical example is Motus, released last December.<\/p>\n\n\n\n![\"On](\"https:\/\/deepinsightai.io\/wp-content\/uploads\/2026\/04\/image-13.png\" "\\"MotuBrain")
<\/figure>\n\n\n\nWhy MotuBrain\u2019s Results Matter<\/h2>\n\n\n\n
Double First Place: Where Does It Win?<\/h2>\n\n\n\n
Who Is Behind It, and What Path Are They Taking?<\/h2>\n\n\n\n