Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive LLM Agent Task Success on ALFWorld Seen
Loading...
89.6
Success Rate
Q-Evolve
76.6
79.975
83.35
86.725
Jun 5, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Q-Evolve
Backbone=Llama-3-8B-In...
2026.06
89.6
ETO + MPO
Backbone=Llama-3-8B-In...
2026.06
85
SFT + MPO
Backbone=Llama-3-8B-In...
2026.06
80.7
KnowAgent
Backbone=Llama-3-8B-In...
2026.06
80
SFT
Backbone=Llama-3-8B-In...
2026.06
79.3
WKM
Backbone=Llama-3-8B-In...
2026.06
77.5
ETO
Backbone=Llama-3-8B-In...
2026.06
77.1
Feedback
Search any
task
Search any
task