Robo Use

GLM-5.3 · Codex · robouse-menagerie

benchflow/robouse-menagerie · Sep 27, 2026 · 8 of 12 solved
Bin a scrap blank and set a fragile vial down gently on a marked square (dual Panda)Solved179 / 1,00079 s
Carry a block from a bowl onto a gold-outlined square and stand it upright (dual Panda)Solved82 / 60048 s
Carry a chess pawn from a bowl onto a gold-outlined square (ALOHA 2)Solved85 / 60045 s
Deliver a payload between two pads without touching a tall protected column (dual Panda)Solved162 / 1,00081 s
Find a pawn in camera images and land it on a gold-outlined square (ALOHA 2)API rejected the imageInfra failureAPI rejected the image0 / 6009 s
Find a target cylinder among protected neighbours in camera images and move it to a tray (dual Panda)API rejected the imageInfra failureAPI rejected the image0 / 80013 s
Infer a composed grid rule from examples and place three tokens accordingly (ALOHA 2)Agent said doneNot solvedAgent said done1,941 / 2,00014.3 min
Infer a grid rule from examples and place three tokens accordingly (dual Panda)Solved482 / 2,000108 s
Lift a target cylinder out of a ring of protected neighbours into a tray (ALOHA 2)Solved134 / 80088 s
Lift a target cylinder out of a ring of protected neighbours into a tray (dual Panda)Agent said doneNot solvedAgent said done117 / 8002.4 min
Place eight chess pieces from two bowls on assigned squares with two arms at once (dual Panda)Time limit reachedNot solvedTime limit reached2,600 / 3,00061.4 min
Place four chess pieces on assigned squares using both arms (ALOHA 2)Agent gave upNot solvedAgent gave up1,972 / 2,00033.2 min
Read each vial's hidden underside label with an upward camera, then pack it by colour (dual Panda)API rejected the imageInfra failureAPI rejected the image0 / 2,50014 s
Seat a peg in a socket under a 6 N contact-force limit (ALOHA 2)Solved179 / 1,20088 s
Turn a keyed peg square to a tight rectangular socket and seat it gently (dual Panda)Solved1,379 / 1,50014.5 min