Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Success on ALFWorld 100 tasks (train)
Loading...
97
Success Rate
TraceRetain-Linear-K50
86.6
89.3
92
94.7
Jun 28, 2026
Success Rate
Updated 26d ago
Evaluation Results
Method
Method
Links
Success Rate
TraceRetain-Linear-K50
Mem=50
2026.06
97
TraceRetain-CEM-K50
Mem=50
2026.06
96
FIFO-K50
Mem=50
2026.06
96
Unbounded
Mem=100
2026.06
96
No memory
Mem=0
2026.06
87
Feedback
Search any
task
Search any
task