ai9stars/HiEviDR-Bench

HiEviDR-Bench HiEviDR-Bench is a benchmark for evaluating Hierarchical Evidence aggregation in multimodal Deep Research. It is designed to assess whether a model can correctly retrieve, connect, and synthesize evidence from large-scale heterogeneous sources, rather than merely producing a fluent final answer or report. Unlike existing benchmarks that mainly focus on final outcomes such as answer correctness, report quality, or citation alignment, HiEviDR-Bench provides… See the full description on the dataset page: huggingface.co/datasets/ai9stars/HiEviDR-Bench.