Aggregate Multimodal Evaluation on Evaluation Suite Average
100Average ScoreLLaVA-1.5 Vanilla 7B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLaVA-1.5 Vanilla 7BVisual Tokens=5762025.08 | 100 | — | |
| MMTokVisual Tokens=1922025.08 | 98.7 | — | |
| VisionZip 🔥Visual Tokens=1922025.08 | 98.4 | — | |
| DivPruneVisual Tokens=1922025.08 | 98 | — | |
| VisionZipVisual Tokens=1922025.08 | 97.9 | — | |
| MMTokVisual Tokens=1282025.08 | 97.8 | — | |
| VisionZip 🔥Visual Tokens=1282025.08 | 97.7 | — | |
| DivPruneVisual Tokens=1282025.08 | 96.9 | — | |
| VisionZipVisual Tokens=1282025.08 | 96.8 | — | |
| MMTokVisual Tokens=642025.08 | 96.6 | — | |
| SparseVLMVisual Tokens=1922025.08 | 95.5 | — | |
| VisionZip 🔥Visual Tokens=642025.08 | 95 | — | |
| DivPruneVisual Tokens=642025.08 | 94.8 | — | |
| VisionZipVisual Tokens=642025.08 | 93.2 | — | |
| SparseVLMVisual Tokens=1282025.08 | 92.9 | — | |
| FastVVisual Tokens=1922025.08 | 89.6 | — | |
| SparseVLMVisual Tokens=642025.08 | 86.9 | — | |
| FastVVisual Tokens=1282025.08 | 84.4 | — | |
| FastVVisual Tokens=642025.08 | 75.6 | — |