UBTECH's Thinker-WM world model claims first place on three embodied AI benchmarks

AIUBTECH says its Thinker-WM world model encodes RGB video, metric depth and robot actions in one shared representation, and that it ranks first on three embodied world model benchmarks in its own evaluation. On WorldOlympiad it scored 0.740 overall, and on EWMBench it reported a total of 4.66. The model was trained on about 30,000 hours of human video, real robot data and simulation, and a technical paper is available on arXiv.

AIUBTech says its Thinker-WM ranks first on WorldOlympiad with a 0.740 composite score, and leads EWMBench with 4.66 and WorldArena Track-1 across 12 metrics. The unified multimodal model jointly models RGB video, depth and robot actions in a shared representation, trained on about 30,000 hours of mixed data, and supports six capability modes.