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

Complex Instruction Tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Environment InteractionComplex Instruction Tasks Interaction
NE1.13
2
Multi-target SearchComplex Instruction Tasks Multi-target
Navigation Error (NE)2.95
2
Dynamic Obstacle AvoidanceComplex Instruction Tasks Avoidance
Navigation Error (NE)0.32
2
Multi-step NavigationComplex Instruction Tasks Multi-step
Navigation Error (NE)0.53
2
Showing 4 of 4 rows