Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Interactive Decision Making on ScienceWorld Unseen

77.81Success Rate

STEP-HRL

0.53820.59940.6660.721Apr 7, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
77.81
2026.04
75.21
2026.04
74.08
2026.04
68.34
2026.04
65.14
2026.04
58.5
2026.04
54.75
2026.04
53.62
2026.04
52.33
2026.04
51.85
2026.04
49.24
2026.04
47.84
2026.04
45.25
2026.04
40.58
2026.04
38.05
2026.04
30.9
2026.04
25.41
2026.04
22.66
2026.04
18.11
2026.04
17.65
2026.04
5.97
2026.04
3.93
2026.04
3.51