oscarqjh/MMSI-Video-Bench_lmmseval download history

oscarqjh/MMSI-Video-Bench_lmmseval is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 100 times (13 in the last 7 days), and 1,721 times in total. It ranks #113,901 among datasets by monthly downloads.

MMSI-Video-Bench A video-based spatial intelligence benchmark for evaluating Multimodal Large Language Models (MLLMs). Dataset Description MMSI-Video-Bench tests models on: Spatial reasoning Motion understanding Planning and prediction Cross-video reasoning Dataset

Open oscarqjh/MMSI-Video-Bench_lmmseval on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.