Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Agent Task on WebArena (evaluation)
Loading...
29.1
Success Rate (SR)
SKILL-DISCO + ReAct
19.636
22.093
24.55
27.007
Jun 25, 2026
Success Rate (SR)
Average Turns
Updated 29d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Turns
SKILL-DISCO + ReAct
Backbone=GPT-4o
2026.06
29.1
5.1
ASIoffline
Backbone=GPT-4o
2026.06
24.6
5.7
ReAct
Backbone=GPT-4o
2026.06
23.9
5.9
SKILL-DISCO + CodeAct
Backbone=GPT-4o
2026.06
22.9
8.5
AWMoffline
Backbone=GPT-4o
2026.06
21.2
5.9
CodeAct
Backbone=GPT-4o
2026.06
20
10.9
Feedback
Search any
task
Search any
task