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

Agentic Task Success on ALFWorld

87.1Success Rate

ALMA

-0.46822.2664567.734Feb 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
87.1
2026.02
80
2026.02
78.6
2026.02
74.8
2026.02
67.6
2026.02
67.1
2026.02
12.4
2026.02
7.6
2026.02
5.7
2026.02
5.2
2026.02
5.2
2026.02
2.9