GLM-5.3 · mini-swe-agent · robouse-menagerie

benchflow/robouse-menagerie · Sep 27, 2026 · 8 of 15 solved

Search tasks


Bin a scrap blank and set a fragile vial down gently on a marked square (dual Panda)	Solved		303 / 1,000	5.1 min
Carry a block from a bowl onto a gold-outlined square and stand it upright (dual Panda)	Solved		117 / 600	92 s
Carry a chess pawn from a bowl onto a gold-outlined square (ALOHA 2)	Solved		131 / 600	3.1 min
Deliver a payload between two pads without touching a tall protected column (dual Panda)	Not solved	Agent said done	426 / 1,000	2.9 min
Find a pawn in camera images and land it on a gold-outlined square (ALOHA 2)	Solved		228 / 600	10.5 min
Find a target cylinder among protected neighbours in camera images and move it to a tray (dual Panda)	Solved		712 / 800	29.9 min
Infer a composed grid rule from examples and place three tokens accordingly (ALOHA 2)	Solved		883 / 2,000	5.3 min
Infer a grid rule from examples and place three tokens accordingly (dual Panda)	Not solved	Agent gave up	786 / 2,000	11.0 min
Lift a target cylinder out of a ring of protected neighbours into a tray (ALOHA 2)	Solved		189 / 800	3.2 min
Lift a target cylinder out of a ring of protected neighbours into a tray (dual Panda)	Solved		619 / 800	5.9 min
Place eight chess pieces from two bowls on assigned squares with two arms at once (dual Panda)	Not solved	Agent exited	1,083 / 3,000	14.4 min
Place four chess pieces on assigned squares using both arms (ALOHA 2)	Not solved	Step budget used up	2,000 / 2,000	10.7 min
Read each vial's hidden underside label with an upward camera, then pack it by colour (dual Panda)	Not solved	Agent gave up	831 / 2,500	28.9 min
Seat a peg in a socket under a 6 N contact-force limit (ALOHA 2)	Not solved	Agent gave up	1,192 / 1,200	13.6 min
Turn a keyed peg square to a tight rectangular socket and seat it gently (dual Panda)	Not solved	Agent gave up	272 / 1,500	10.7 min