Rapidata/text-to-video-human-preferences-823k
Viewer • Updated • 47.2k • 185 • 9
Human judgements of text-to-video and image-to-video models. Start with the consolidated 823k-vote set.
Note All 17 text-to-video models in one chosen/rejected table, 823,169 votes
Note benchmark.ai/world-model-physics
Note benchmark.ai/world-model-physics-v2
Note benchmark.ai/world-models-realism
Note benchmark.ai/camera-movement
Note benchmark.ai/relative-camera-movement
World models physics benchmark, ranked by humans
World models realism benchmark, ranked by humans
World models camera movement benchmark, ranked by humans
World models relative camera benchmark, ranked by humans