Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Agent Action Prediction on ALFWorld
Loading...
65
Accuracy
DPO+
54.6
57.3
60
62.7
Jun 25, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
DPO+
Backbone=Qwen3-8B
2026.06
65
SFT+
Backbone=Qwen3-8B
2026.06
63
FRODO
Backbone=Qwen3-8B
2026.06
61
DPO
Backbone=Qwen3-8B
2026.06
59
SFT
Backbone=Qwen3-8B
2026.06
55
Feedback
Search any
task
Search any
task