Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Natural QA on MM-Vet
Loading...
37.4
Score
Baseline
30.952
32.626
34.3
35.974
Mar 17, 2025
Score
Updated 2d ago
Evaluation Results
Method
Method
Links
Score
Baseline
Model=LLaVA-13B, Ratio...
2025.03
37.4
HiMAP
Model=LLaVA-13B, Ratio...
2025.03
37.4
FastV
Model=LLaVA-13B, Ratio...
2025.03
35.5
HiMAP
Model=LLaVA-7B, Ratio=34%
2025.03
33.7
Baseline
Model=LLaVA-7B, Ratio=...
2025.03
33.4
FastV
Model=LLaVA-7B, Ratio=54%
2025.03
31.2
Feedback
Search any
task
Search any
task
