Task difficulty is uneven
Carrying a rigid box is not the same problem as folding laundry. Opening a dishwasher is not the same as sorting fragile items. Decompose chores into perception, navigation, grasping, tool use, deformable objects and recovery.
Dishes are a benchmark
Figure has demonstrated Helix 02 unloading and reloading a dishwasher. The useful buyer question is how success transfers across different kitchens, dishware and interruptions.
Tidying needs semantics
“Tidy the room” requires knowing where objects belong, what counts as trash and what should remain untouched. That is a long sequence of context-sensitive decisions.
Laundry remains hard
Cloth changes shape, hides geometry and tangles. Folding and sorting are strong tests of perception and dexterity.
Build an acceptance test
List ten tasks, the conditions in your home, expected quality, maximum supervision and the failure behavior you can tolerate. That turns marketing into a fit test.