Behavioral Cloning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95Rate
18
Jun 23, 2026
0.231Relative L2 Error
16
Apr 7, 2026
0.057Relative L2 Error
16
Apr 7, 2026
0.075Relative L2 Error
16
Apr 7, 2026
4.4Relative L2 Error
16
Apr 7, 2026
0.081Relative L2 Error
15
Apr 7, 2026
72Task Completion Accuracy
4
Feb 26, 2026
96Task Completion Accuracy
4
Feb 26, 2026
100Task Completion Accuracy
4
Feb 26, 2026
98.12Accuracy
2
Mar 11, 2026