vanyacohen/MET-Bench-Chess download history

vanyacohen/MET-Bench-Chess is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,826 times (123 in the last 7 days), and 1,826 times in total. It ranks #12,124 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

Open vanyacohen/MET-Bench-Chess on Hugging Face

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