SOTA Task Planning benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
EB-ALFRED Base		Success Rate (SR)96	34	24d ago
RestBench TMDB	SGC	Node F182.63	25	1mo ago
TaskBench Daily Life	Direct	Node-F197.36	25	1mo ago
TaskBench Multimedia	SGC	Node F188.54	25	1mo ago
Hugging Face	SGC	Node-F177.79	25	1mo ago
MomaGraph-Bench Overall 1.0		Accuracy73.9	20	1mo ago
MomaGraph-Bench Tier 4 1.0		Accuracy69.5	20	1mo ago
MomaGraph-Bench 1.0 (Tier 3)		Accuracy75	20	1mo ago
MomaGraph-Bench Tier 2 1.0	MomaGraph-R1	Accuracy71.9	20	1mo ago
MomaGraph-Bench 1.0 (Tier 1)		Accuracy83.7	20	1mo ago
EB-Habitat Long	GPT-4o	Success Rate (SR)64	17	24d ago
EB-ALFRED (Long)		Success Rate (SR)70	17	24d ago
Hugging Face v1 (test)	SGC	n-F177.79	17	1mo ago
TaskBench Multimedia v1 (test)	SGC	n-F188.54	14	1mo ago
EgoPlan-Benchmark 2	PhysBrain-8B	Accuracy46.9	11	1mo ago
EgoPlan-Benchmark1 (val)	PhysBrain-8B	Accuracy47.4	11	1mo ago
3DSG 141 tasks modified and original variants (test)	CM w/ Relaxation	Success Rate (Planning only)99.02	9	1mo ago
Table Clean Sim SE2 (test)		Success Rate100	9	1mo ago
Table Clean Sim SE2 distribution (train)		Success Rate100	9	1mo ago
Blocks Vec3 (test)		Success Rate100	9	1mo ago
Blocks Vec3 distribution (train)		Success Rate100	9	1mo ago
Satellites SE2 (test)		Success Rate100	9	1mo ago
Satellites SE2 (train)		Success Rate100	9	1mo ago
Packing Image (test)		Success Rate100	8	1mo ago
Packing Image (train)		Success Rate1	8	1mo ago

Showing 25 of 66 rows