Long-horizon tasks
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
30.29Success Rate
7
Apr 30, 2026
17.36Success Rate (SR)
7
Apr 30, 2026
21.69Success Rate (SR)
7
Apr 30, 2026
51.82Success Rate (SR)
7
Apr 30, 2026
94.53Success Rate (SR)
7
Apr 30, 2026
97.47Success Rate (SR)
7
Apr 30, 2026