DramaChain Bench is a benchmark for the complete short-drama production pipeline, spanning script, storyboard, keyframes, shots, and final episodes. It comprises DramaChain Dimensions (five evaluation axes with 63 leaf dimensions), DramaChain Agent (calibrated against commercial platforms), and a labeling system with professional annotations across 5,785 items. An agentic judge automatically scores dimensions by gathering evidence across multiple rounds, reaching 0.918 PLCC correlation with human rankings, and the authors show upstream defects propagate through later production stages.
