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

Task Success on ALFWorld (test)

94.23Success Rate

MetaSkill-Evolve

90.22691.265592.30593.3445Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
94.23
2026.07
92.31
2026.07
92.31
2026.07
90.38