vanyacohen/MET-Bench-Minecraft
Viewer • Updated • 8k • 826
MET-Bench
-
-
vanyacohen/MET-Bench-Chess
Viewer • Updated • 107k • 677 -
vanyacohen/MET-Bench-Shell
Viewer • Updated • 57k • 148 -
vanyacohen/MET-Bench-Minecraft-Trajectories
Viewer • Updated • 463k • 77 -
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
Paper • 2502.10886 • Published