A new benchmark called WorldReasonBench tests video generators not on image quality, but on physical and logical plausibility. ByteDance's Seedance 2.0 leads the field ahead of Veo 3.1 and Sora 2, with commercial models scoring roughly twice as high as open-source alternatives. Logical reasoning remains the hardest category for every model by a wide margin.

The jump from pixel generator to actual world model still hasn't happened. The article New benchmark confirms AI video generators look stunning but still can't reason about the world appeared first on The Decoder.