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

Household Task Execution on AlfWorld (test)

97.01Success Rate

A-Mem

7.757230.928654.177.2714May 8, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
97.01
2026.05
92.54
2026.05
92.54
2026.05
92.54
2026.05
91.45
2026.05
91.04
2026.05
90.3
2026.05
88.81
2026.05
88.72
2026.05
86.56
2026.05
82.16
2026.05
76.12
2026.05
74.62
2026.05
70.89
2026.05
67.16
2026.05
62.69
2026.05
62.69
2026.05
61.19
2026.05
46.27
2026.05
42.54
2026.05
41.04
2026.05
36.57
2026.05
12.69
2026.05
11.19