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

Embodied Task Completion on ALFWorld (IOD)

96.67Accuracy

SKILLGEN

58.533268.434178.33588.2359May 9, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
96.677.33
2026.05
9411.33
2026.05
89.33-
2026.05
867.33
2026.05
82.67-
2026.05
78.67-
2026.05
77.3313.33
2026.05
77.3310.67
2026.05
70.672.67
2026.05
68-
2026.05
66.676.67
2026.05
66.67-
2026.05
64-
2026.05
63.33-
2026.05
62.67-0.67
2026.05
60-