Stack

Benchmarks

Dataset Name	SOTA Method	Metric
PandaGym Stack	Ours Ens	Success Rate98.4	15	1d ago
Robosuite 1.4 (test)		IQM73	12	3mo ago
Real-world robot platform (evaluation)		Success Rate30	6	15d ago
PDDLLM v1 (test)		Planning Success Rate98.5	6	3mo ago
RLBench Sim2sim Shared Object - Stack		Success Rate86.67	6	3mo ago
Realman robot collected dataset Real-world In-Domain 1.0 (test)	CogACT	Success Rate (Cup)83.3	5	3mo ago
OneACTPlay	LLM Trainer	Success Rate89	4	1d ago
EasyMimic Dataset 1.0 (test)	EasyMimic	Average Score0.7	4	3mo ago
RoboSuite	Slot-MPC	Success Rate42	4	19d ago
Real-world Stacking Cup	OCRA	Success Rate1	3	2mo ago
Real Robot	EmboAlign	Success Rate7	3	2mo ago
RoboSuite (out-of-distribution)	GAP	Success Rate72	3	3mo ago
ManiSkill Stack		Success Rate80	2	20d ago
Robosuite IIWA (Robotiq140) few-shot transfer	ICon-Diff-C	Success Rate4.7	2	3mo ago
Robosuite Kinova (Robotiq85) few-shot transfer	ICon-Diff-C	Success Rate5.3	2	3mo ago
Robosuite Franka (Default Gripper) few-shot transfer	ICon-Diff-C	Success Rate22	2	3mo ago
Stack task environment	Act–Observe–Rewrite	Success Rate91	1	2mo ago

Showing 17 of 17 rows