Behavior
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
BEHAVIOR-1K B-100 1.0
97.5SP%
17
BEHAVIOR-1K B-1000 1.0
97.3Success Rate (SP)
17
BEHAVIOR-1K 15 tasks
100BT Valid
14
Behavior
87.08MRA
12
BEHAVIOR-1K
44.7Fitting
12
Mini-BEHAVIOR OOD
83Success Rate
11
MiniBehavior size 20
72.96Success Rate
11
MiniBehavior size 16
79.84Success Rate
11
MiniBehavior size 12
91.27Success Rate
11
BEHAVIOR-1K
100Success Rate
11
BEHAVIOR-1K (test)
76ROC-AUC
8
MINIBEHAVIOR
7,580EM
8
Behavior Shifted Environment (test)
1.02Testing Reward
8
BEHAVIOR-1K (val)
28Success Count
7
BEHAVIOR-1K Task 26
52.5Task Progress
5
BEHAVIOR-1K (Simulation)
51Radio Score
5
BEHAVIOR 2025 (private)
12.4Binary Success
5
BEHAVIOR 2025 (public)
14.4Binary Success
5
Behavior-1K
84.4Success Rate
5
BEHAVIOR-1K
0.56Q-Score
4
BEHAVIOR-1K seeds 1-25 (held-out)
100Nav Success Rate
3
BEHAVIOR-1K seeds 1-25 (held-out)
92Navigation Success Rate
3
BEHAVIOR
84Navigational Success Rate
3
BEHAVIOR
88Navigation Success Rate
3
Behavior
43.66Execution Time (s)
3