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

Embodied Decision Making on ALFWorld held-out (test)

95.5Score

SkillOpt

25.71643.83361.9580.067May 22, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.05
95.5
2026.05
93.3
2026.05
91.8
2026.05
91
2026.05
87.3
2026.05
85.8
2026.05
85.8
2026.05
85.1
2026.05
83.6
2026.05
83.6
2026.05
82.8
2026.05
82.8
2026.05
82.8
2026.05
82.1
2026.05
81.3
2026.05
81.3
2026.05
78.4
2026.05
76.9
2026.05
76.1
2026.05
75.4
2026.05
74.6
2026.05
74.6
2026.05
73.9
2026.05
73.1
2026.05
73.1
2026.05
70.9
2026.05
70.9
2026.05
69.4
2026.05
68.7
2026.05
68.7
2026.05
68.7
2026.05
67.9
2026.05
65.7
2026.05
65.7
2026.05
64.9
2026.05
60.4
2026.05
60.4
2026.05
59.7
2026.05
58.2
2026.05
56.7
2026.05
56.7
2026.05
55.2
2026.05
53.7
2026.05
44.8
2026.05
42.5
2026.05
34.3
2026.05
30.6
2026.05
29.9
2026.05
28.4