Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Element Grounding on Multimodal-Mind2Web Cross-Task
Loading...
50.7
Element Accuracy
UGround-V1-7B
26.052
32.451
38.85
45.249
Oct 7, 2024
Element Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Element Accuracy
UGround-V1-7B
Input=Image (SeeAct-V)...
2024.10
50.7
UGround-V1-2B
Input=Image (SeeAct-V)...
2024.10
48.6
UGround-V1-7B
Input=Image (SeeAct-V)...
2024.10
48.5
UGround
Input=Image (SeeAct-V)...
2024.10
47.7
UGround-V1-2B
Input=Image (SeeAct-V)...
2024.10
47.7
UGround
Input=Image (SeeAct-V)...
2024.10
46.6
Choice
Input=Image + Text, Pl...
2024.10
46.4
UGround
Input=Image (SeeAct-V)...
2024.10
45.1
UGround
Input=Image (SeeAct-V)...
2024.10
44.6
Choice
Input=Image + Text, Pl...
2024.10
42.4
SeeClick
Input=Image (SeeAct-V)...
2024.10
33.5
SeeClick
Input=Image (SeeAct-V)...
2024.10
32.1
SeeClick
Input=Image (SeeAct-V)...
2024.10
30.7
SeeClick
Input=Image (SeeAct-V)...
2024.10
29.7
SoM
Input=Image + Text, Pl...
2024.10
29.6
SoM
Input=Image + Text, Pl...
2024.10
27
Feedback
Search any
task
Search any
task