Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generation on MLLMU-Bench (Forget Set)
Loading...
64.5
Rouge Score
Vanilla
47.444
51.872
56.3
60.728
Feb 21, 2025
Rouge Score
Factuality Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rouge Score
Factuality Score
Vanilla
Base Model=LLaVA-1.5-7...
2025.02
64.5
6.78
Vanilla
Base Model=LLaVA-1.5-7...
2025.02
59.4
6.4
Vanilla
Base Model=LLaVA-1.5-7...
2025.02
57.5
6.34
MANU
Base Model=LLaVA-1.5-7...
2025.02
50.3
3.48
MANU
Base Model=LLaVA-1.5-7...
2025.02
49.1
3.27
GA
Base Model=LLaVA-1.5-7...
2025.02
48.5
3.38
MANU
Base Model=LLaVA-1.5-7...
2025.02
48.1
3.73
Feedback
Search any
task
Search any
task