Visual captioning benchmarks have become outdated with the emergence of modern MLLMs, as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. We introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions using F1-score. By converting annotations to QA pairs, we further introduce a heuristic metric, know but cannot tell ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides the first holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of capabilities.

An example of image caption (left) and video caption (right). By analyzing the components of captions, we conclude 12 dimensions (9 static dimensions and 4 dynamic dimensions with object number shares on both static and dynamic), which all contribute to a detailed and comprehensive caption. The static dimensions are shared in both images and videos. For video data, there are additional dynamic dimensions as they need to be judged with temporal relations.