Sequential Decision Making
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
16.7Average Reward
30
May 26, 2026
28.5Average Reward
30
May 26, 2026
-2.3Average Reward
30
May 26, 2026
96.27Success Rate
26
Mar 13, 2026
4.7Average Steps per Episode
18
Mar 13, 2026
0.88Score
11
Feb 26, 2026
270.5Score (Detective)
9
Apr 2, 2026
68.4Success Rate
6
Apr 23, 2026
60.4Success Rate
6
Apr 23, 2026
19.5Cumulative Return
5
Jun 11, 2026
22.89Cumulative Return
5
Jun 11, 2026
21.33Cumulative Return
5
Jun 11, 2026
150.3Cumulative Return
5
Jun 11, 2026
31.8Cumulative Return
5
Jun 11, 2026
71.5Normalized Success Rate
5
Jun 11, 2026
70.4Pass@1 Success Rate
4
Feb 26, 2026
14.8Rollout Length
3
Jul 1, 2026
43.9Rollout Length
3
Jul 1, 2026
89Success Rate
3
Jun 23, 2026
0.756Reward
3
Feb 26, 2026
0.455Reward
3
Feb 26, 2026
0.307Reward
3
Feb 26, 2026
3.54Mean Regret
2
Jun 4, 2026
0.697Mean Regret
2
Jun 4, 2026
0.079Mean Regret
2
Jun 4, 2026