This benchmark ranks world and video generation models on whether they can carry out a camera movement stated in plain terms, without referencing the scene, such as moving forward, tilting down or rolling clockwise, starting from a single still image. We curated 30 camera-movement instructions across 22 spaces and mixed and matched them into 600 prompts, held fixed to ensure reproducibility of the results. The rankings are updated continuously from 513,079 responses across 102,595 pairwise human-preference matches. All data and judgments are public; see the methodology for details on evaluation and scoring.
We use crowd intelligence to deliver real, diverse human feedback at scale for model evaluation and post-training.