This benchmark ranks text-to-image models using human comparisons of images generated from the same prompt. We curated 1,514 prompts across 25 categories, focusing on commercial applicability and ensuring reproducibility of the results. The rankings are updated continuously from 7,789,896 responses across 1,558,555 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.