Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web Task Automation on WorkArena L1
Loading...
68
Average Reward
JEF-HINTER
39.92
47.21
54.5
61.79
Oct 5, 2025
Average Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Reward
JEF-HINTER
Base Model=GPT-5-mini
2025.10
68
Human hints
Base Model=GPT-5-mini
2025.10
66
Documentation
Base Model=GPT-5-mini
2025.10
64
ReAct
Base Model=GPT-5-mini
2025.10
61
JEF-HINTER
Base Model=GPT-5-nano
2025.10
48
Documentation
Base Model=GPT-5-nano
2025.10
44
Human hints
Base Model=GPT-5-nano
2025.10
43
ReAct
Base Model=GPT-5-nano
2025.10
41
Feedback
Search any
task
Search any
task