Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MAT2-THOR

Benchmarks

Task NameDataset NameSOTA ResultTrend
PlanningMAT2-THOR Overall
Planning Time (s)12.83
5
PlanningMAT2-THOR Vague
Planning Time (s)13.1
5
PlanningMAT2-THOR Complex
Planning Time (s)15.7
5
PlanningMAT2-THOR Simple
Planning Time (s)10.8
5
Multi-agent planning and executionMAT2-THOR Overall Tasks
TCR78
5
Multi-agent planning and executionMAT2-THOR Vague Tasks
Task Completion Rate (TCR)71
5
Multi-agent planning and executionMAT2-THOR Complex Tasks
TCR59
5
Multi-agent planning and executionMAT2-THOR Simple Tasks
TCR92
5
Showing 8 of 8 rows