Decision Making
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
41.71Mean Hourly Profit
121
Jun 15, 2026
6.4Steps
22
Mar 13, 2026
66.42ALFWorld Success Rate
21
Jun 30, 2026
42.9Success Rate
15
Mar 10, 2026
2.55Mean Rank
14
Apr 7, 2026
58.9ACC
13
Feb 26, 2026
47.9Accuracy
13
Feb 26, 2026
60Success Rate
9
Jun 15, 2026
59.88Success Rate (SR)
9
May 8, 2026
61.19Success Rate (SR)
9
May 8, 2026
63.57Success Rate (SR)
9
May 8, 2026
90.2Top-1 Accuracy
8
Apr 21, 2026
79Top-1 Acc.
8
Apr 21, 2026
78.8Top-1 Accuracy
8
Apr 21, 2026
61.4Accuracy
8
Feb 26, 2026
25.001Reward
7
Jun 25, 2026
0.5Score
7
Jun 23, 2026
3Payoff
7
Jun 23, 2026
2Payoff
7
Jun 23, 2026
0.504Timely Score
7
Mar 11, 2026
35.52Timeliness Score
7
Mar 11, 2026
0.545Timely Score
7
Mar 11, 2026
0.785Micro Aggregation Score
7
Feb 26, 2026
83.4Micro Avg
7
Feb 26, 2026
48.3Vignette Score
6
Apr 30, 2026