Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Agent Task on ALFWorld unseen
Loading...
99.3
Success Rate (SR)
SKILL-DISCO + CodeAct
44.908
59.029
73.15
87.271
Jun 25, 2026
Success Rate (SR)
Average Turns
Updated 29d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Turns
SKILL-DISCO + CodeAct
Backbone=GPT-4o
2026.06
99.3
3.2
CodeAct
Backbone=GPT-4o
2026.06
96.3
3.6
SKILL-DISCO + ReAct
Backbone=GPT-4o
2026.06
92.4
8.8
ReAct
Backbone=GPT-4o
2026.06
82
19.3
AWMoffline
Backbone=GPT-4o
2026.06
54.5
11.3
ASIoffline
Backbone=GPT-4o
2026.06
47
11.4
Feedback
Search any
task
Search any
task