Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Understanding on MM-Vet (5% Forget Set)
Loading...
43.9
Average Score
Vanilla
28.3208
32.3654
36.41
40.4546
Feb 21, 2025
Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Score
Vanilla
Base Model=Idefics2, F...
2025.02
43.9
MANU
Base Model=Idefics2, F...
2025.02
40.83
NPO
Base Model=Idefics2, F...
2025.02
40.22
KL Minim.
Base Model=Idefics2, F...
2025.02
38.61
Grad. Diff
Base Model=Idefics2, F...
2025.02
36.67
GA
Base Model=Idefics2, F...
2025.02
35.12
Vanilla
Base Model=LLaVA, Forg...
2025.02
34.08
MANU
Base Model=LLaVA, Forg...
2025.02
32.76
NPO
Base Model=LLaVA, Forg...
2025.02
32.38
KL Minim.
Base Model=LLaVA, Forg...
2025.02
31.29
Grad. Diff
Base Model=LLaVA, Forg...
2025.02
30.28
GA
Base Model=LLaVA, Forg...
2025.02
28.92
Feedback
Search any
task
Search any
task