Robot Task Planning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.1Object Omission Rate
6
Mar 12, 2026
28.5Object Omission Rate
6
Mar 12, 2026
0.168Object Omission Rate
6
Mar 12, 2026
55Success Rate
4
Apr 20, 2026
73Success Rate
4
Apr 20, 2026
65Success Rate
4
Apr 20, 2026
99Token Cost (k)
4
Feb 26, 2026
50Token Cost (k)
4
Feb 26, 2026
36Token Cost (k)
4
Feb 26, 2026
212Token Cost (k)
4
Feb 26, 2026
72Success Rate
3
Apr 20, 2026
86Success Rate
3
Apr 20, 2026
78.1Success Rate
2
Feb 26, 2026
74.5Success Rate
2
Feb 26, 2026
87.1Success Rate
2
Feb 26, 2026
100Success Rate
2
Feb 26, 2026
1Success Rate
2
Feb 26, 2026
100Success Rate
2
Feb 26, 2026
1Success Rate
2
Feb 26, 2026
100Success Rate
2
Feb 26, 2026