Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web Navigation on Multimodal-Mind2Web Average
Loading...
54.3
Avg. Step Success Rate
Explorer-7B
16.132
26.041
35.95
45.859
Feb 17, 2025
Avg. Step Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg. Step Success Rate
Explorer-7B
Evaluation Protocol=Su...
2025.02
54.3
AgentTrek-7B
Evaluation Protocol=Su...
2025.02
53.2
Explorer-4B
Evaluation Protocol=Su...
2025.02
49.8
Explorer-7B
Evaluation Protocol=Su...
2025.02
49.5
Explorer-4B
Evaluation Protocol=Su...
2025.02
44.8
Explorer-7B
Evaluation Protocol=Su...
2025.02
43
Explorer-4B
Evaluation Protocol=Su...
2025.02
37.4
SeeAct
Evaluation Protocol=In...
2025.02
36.5
ScribeAgent-32B
Evaluation Protocol=Su...
2025.02
35.1
GPT-4
Evaluation Protocol=In...
2025.02
29.7
EDGE-9.6B
Evaluation Protocol=Su...
2025.02
24.5
SeeClick-9.6B
Evaluation Protocol=Su...
2025.02
20.9
GPT-3.5
Evaluation Protocol=In...
2025.02
18.3
MiniCPM-3.1B
Evaluation Protocol=Su...
2025.02
17.6
Feedback
Search any
task
Search any
task