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

Interactive Task Solving on ALFWorld Small context window

95.8Pick Success Rate

Slide Window

48.16860.53472.985.266Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
95.800066.723.529.1
2026.06
87.500016.7017.9
2026.06
87.574.221.74.872.270.656.7
2026.06
83.36.54.34.833.335.327
2026.06
83.300027.8018.7
2026.06
750005.6014.2
2026.06
70.800016.7015
2026.06
503.21323.8017.617.9