Visual Language Model Evaluation on MME
1,842MME ScoreVanilla
Evaluation results
| Method | Links | ||
|---|---|---|---|
| VanillaModel=LLaVA-Next-7B, Token Budget=2880, Reduction Ratio=0%2026.05 | 1,842 | 100 | |
| SPprunerModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,730 | 97.7 | |
| VisionZipModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,715 | 96.2 | |
| DivPruneModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,702 | 96.1 | |
| DARTModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,697 | 96.4 | |
| FastVModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,661 | 86.8 | |
| PyramidDropModel=LLaVA-Next-7B, Token Budget=320, Reduction Ratio=88.9%2026.05 | 1,660 | 90.1 |