MS-Bench

This is MS-Bench, the first comprehensive benchmark co-developed with archaeologists, comprising 5,076 high-resolution images from 4th to 14th century and 9,982 expert-curated questions across nine sub-tasks aligned with archaeological workflows. Through four prompting strategies, we systematically evaluate 32 LMMs on their: effectiveness robustness cultural contextualization本数据集为MS-Bench，是首个与考古学家联合研发的综合基准测试集。其包含公元4世纪至14世纪的5076张高分辨率图像，以及9982道由专家精心编撰的问题，涵盖9个贴合考古工作流程的子任务。研究团队通过四种提示策略，系统评估了32款大语言多模态模型（Large Multimodal Model, LMM）在有效性、鲁棒性与文化语境适配能力三个维度的性能表现。