vanyacohen/MET-Bench-Shell download history
vanyacohen/MET-Bench-Shell is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 325 times (37 in the last 7 days), and 325 times in total. It ranks #46,117 among datasets by monthly downloads.
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models Vanya Cohen and Raymond Mooney · ICML 2026 Paper · Project page · Load the dataset · Citation Domains: Chess · Shell Game · Minecraft MET-Bench evaluates entity state tracking