Today, we're excited to introduce the release of Labelbox leaderboards - an innovative and scientific process for ranking multimodal AI models that goes beyond conventional benchmarks.
Our approach delivers structured evaluations on subjective AI model outputs using human experts and a rigorous process that provides detailed feature-level metrics and multiple ratings.
Check out the first set of leaderboards now available for image generation, speech generation, and video generation. We'd love to hear your feedback and suggestions on specific models to include, and we're excited to drive the field toward more meaningful, human-aligned progress that truly captures the capabilities of next-generation AI models.