Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Decision Making on ALFWorld (qualitative context)
Loading...
99
Success Rate (SR)
RAFA
34.52
51.26
68
84.74
Mar 18, 2026
Success Rate (SR)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
RAFA
Backbone / Agent=GPT-4...
2026.03
99
RPMS
Backbone / Agent=Claud...
2026.03
98.5
Reflexion
Backbone / Agent=GPT-3...
2026.03
97
RPMS
Backbone / Agent=Llama...
2026.03
88.1
A3T
Backbone / Agent=Train...
2026.03
86
ReAct
Backbone / Agent=PaLM-...
2026.03
70.9
RPMS
Backbone / Agent=Llama...
2026.03
59.7
BUTLER8
Backbone / Agent=Train...
2026.03
37
Feedback
Search any
task
Search any
task