Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Decision Making on ALFWorld Unseen v1
Loading...
61.19
Success Rate (SR)
BeliefMem
16.9588
28.4419
39.925
51.4081
May 7, 2026
Success Rate (SR)
Average Steps
Updated 26d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Steps
BeliefMem
Backbone=Qwen3-Next-80...
2026.05
61.19
29.34
ReadAgent
Backbone=Qwen3-Next-80...
2026.05
54.48
27.41
BeliefMem
Backbone=Qwen3-Next-80...
2026.05
53.75
30.49
Mem0
Backbone=Qwen3-Next-80...
2026.05
41.04
33.16
MemoryBank
Backbone=Qwen3-Next-80...
2026.05
38.06
34.99
LangMem
Backbone=Qwen3-Next-80...
2026.05
31.34
37.17
A-MEM
Backbone=Qwen3-Next-80...
2026.05
29.1
39.04
No-Memory
Backbone=Qwen3-Next-80...
2026.05
26.12
39.35
MemoryOS
Backbone=Qwen3-Next-80...
2026.05
18.66
42.95
Feedback
Search any
task
Search any
task