Interactive Decision-making
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.6Overall Success Rate
398
Jul 3, 2026
96.87Success Rate
81
Jun 30, 2026
69.97Success Rate
78
Jun 11, 2026
84.02Success Rate
77
Jul 7, 2026
88.8Success Rate
72
May 19, 2026
97.76Success Rate
67
Jul 7, 2026
99.6Success Rate
60
Jun 4, 2026
97.86Success Rate
47
Jul 7, 2026
79.6Success Rate
40
Apr 21, 2026
62.3Average Reward
40
Apr 21, 2026
97Success Rate
37
May 19, 2026
100Pick Reward
33
Jul 7, 2026
85.15Success Rate
32
May 19, 2026
63.3Success Rate
31
Jun 11, 2026
39Real
24
Apr 16, 2026
100Real
24
Apr 16, 2026
58.94Success Rate
24
Feb 26, 2026
0.735Average Reward
20
Apr 28, 2026
88.81Average Reward
20
Apr 28, 2026
56.43Success Rate
18
Jun 4, 2026
9.9Score
14
Apr 28, 2026
53.8Score
14
Apr 28, 2026
67.3Score
12
Jun 5, 2026
85.8Score
11
Jul 7, 2026
91.73Avg@4 (Least-Time)
10
Jul 8, 2026