Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web Navigation on Mind2Web
Loading...
62.3
Success Rate (Cross-Task)
CogAgent
10.612
24.031
37.45
50.869
Dec 14, 2023
Success Rate (Cross-Task)
Success Rate (Cross-Website)
Success Rate (Cross-Domain)
Overall Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate (Cross-Task)
Success Rate (Cross-Website)
Success Rate (Cross-Domain)
Overall Success Rate
CogAgent
Representations of scr...
2023.12
62.3
54
59.4
58.2
LLaMA2-70B
Representations of scr...
2023.12
55.8
51.6
55.7
54.4
LLaMA2-7B
Representations of scr...
2023.12
52.7
47.1
50.3
50.1
Flan-T5XL
Representations of scr...
2023.12
52
38.9
39.6
43.5
CogVLM
Representations of scr...
2023.12
37.1
23.4
26.3
23.9
GPT-4
Representations of scr...
2023.12
36.2
30.1
26.4
30.9
GPT-3.5
Representations of scr...
2023.12
18.6
17.4
16.2
17.4
Qwen-VL
Representations of scr...
2023.12
12.6
10.1
8
10.2
Feedback
Search any
task
Search any
task