InkSlop Benchmark A vibe-coded benchmark for spatial reasoning with digital ink. amaksay/inkslop-overlap-hard Updated Jan 26 • 8 amaksay/inkslop-autocomplete-hard Preview • Updated Jan 26 • 196 amaksay/inkslop-derender-hard Updated Jan 26 • 12 amaksay/inkslop-mazes-hard Viewer • Updated Jan 26 • 550 • 3.92k
InkSlop Benchmark A vibe-coded benchmark for spatial reasoning with digital ink. amaksay/inkslop-overlap-hard Updated Jan 26 • 8 amaksay/inkslop-autocomplete-hard Preview • Updated Jan 26 • 196 amaksay/inkslop-derender-hard Updated Jan 26 • 12 amaksay/inkslop-mazes-hard Viewer • Updated Jan 26 • 550 • 3.92k
Sleeping Agents 2 InkSlop Benchmark Viewer ✍ View and compare results from the InkSlop benchmark datasets
