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

Household Manipulation on ALFWorld (Seen)

84.65Average Reward

SkillReranker

47.126856.868466.6176.3516Jul 7, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
84.6515.48
2026.07
80.7216.31
2026.07
78.5712.06
2026.07
75.3617.21
2026.07
74.2912.61
2026.07
72.512.89
2026.07
70.7213.62
2026.07
70.3617.55
2026.07
67.517.55
2026.07
62.517.64
2026.07
58.5720.04
2026.07
48.5719.62