Real-world Long-Horizon Tasks
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Real-world Long-Horizon Tasks (seen environment)
40Task Success Rate: Make coffee
6
Real-world Long-horizon Tasks
77.8Clothes Folding Success Rate
4
Real-world Long-horizon Tasks
0.85Success Rate
4
Real-world Long-horizon Tasks
70Success Rate
4
Real-world Long-horizon Tasks
90Success Rate
4
Real-world Long-horizon Tasks
95Success Rate
4
Real-world Long-horizon Tasks
85Success Rate
4