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

Task Success on ALFWorld Clean (T=100)

97.5Task Success Rate

Unbounded

85.5488.64591.7594.855Jun 28, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
97.59,499
2026.06
97.59,499
2026.06
969,298
2026.06
969,298
2026.06
868,090