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

Embodied Task Completion on ALFWorld ID

94.3Pick Success Rate

SKILL0

25.97243.71161.4579.189May 27, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
94.37681.585.13.8
2026.05
94.38896.393.11.3
2026.05
91.48081.585.14.3
2026.05
91.48496.390.82.7
2026.05
91.48470.482.84.5
2026.05
88.65281.575.96.2
2026.05
85.74444.460.910.3
2026.05
85.75270.371.37.7
2026.05
804466.765.59.5
2026.05
807288.980.56.2
2026.05
74.31255.650.612.7
2026.05
71.42833.347.113.3
2026.05
71.41644.447.113.3
2026.05
65.71233.340.215.3
2026.05
65.72051.948.313.2
2026.05
62.9446357.512
2026.05
54.3418.528.717.5
2026.05
28.61218.520.717.2