Multi-modal Vision-Language Evaluation on MMVet
46.8AccuracyVisionZip
Evaluation Results
| Method | Links | |
|---|---|---|
| VisionZipBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 46.8 | |
| VisPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 46.1 | |
| VisPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=960, Pruning Ratio=66.7%2026.02 | 45 | |
| FSRBackbone=LLaVA-NeXT-13B, Tokens Retained=960, Pruning Ratio=66.7%2026.02 | 44.7 | |
| FSRBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 44.1 | |
| FastVBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 43.8 | |
| HoloVBackbone=LLaVA-NeXT-13B, Tokens Retained=960, Pruning Ratio=66.7%2026.02 | 42.3 | |
| FSRBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 42.3 | |
| CDPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 42.1 | |
| CDPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=960, Pruning Ratio=66.7%2026.02 | 41.7 | |
| CDPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 41.4 | |
| HoloVBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 41.3 | |
| VisionZipBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 41.1 | |
| HoloVBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 40.7 | |
| VisPrunerBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 39.7 | |
| DivPruneBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 39.2 | |
| DivPruneBackbone=LLaVA-NeXT-13B, Tokens Retained=640, Pruning Ratio=77.8%2026.02 | 39 | |
| LaSCDBackbone=GLM-4V2026.05 | 38.8 | |
| MemVRBackbone=GLM-4V2026.05 | 38.2 | |
| RegularBackbone=GLM-4V2026.05 | 37.6 | |
| LLaVA-NeXT-13BBackbone=LLaVA-NeXT-13B, Tokens Retained=2880, Pruning Ratio=0%2026.02 | 36.6 | |
| DeCoBackbone=GLM-4V2026.05 | 34.4 | |
| VCDBackbone=GLM-4V2026.05 | 33.6 | |
| LaSCDBackbone=LLaVA-1.52026.05 | 33.4 | |
| MemVRBackbone=Qwen-VL2026.05 | 33.4 | |
| LaSCDBackbone=Qwen-VL2026.05 | 32.8 | |
| ICDBackbone=GLM-4V2026.05 | 32.5 | |
| MemVRBackbone=LLaVA-1.52026.05 | 32.4 | |
| OPERABackbone=LLaVA-1.52026.05 | 32 | |
| DeCoBackbone=Qwen-VL2026.05 | 31.5 | |
| RegularBackbone=Qwen-VL2026.05 | 31.1 | |
| FastVBackbone=LLaVA-NeXT-13B, Tokens Retained=320, Pruning Ratio=88.9%2026.02 | 30.2 | |
| RegularBackbone=LLaVA-1.52026.05 | 27.5 | |
| VCDBackbone=LLaVA-1.52026.05 | 26.7 | |
| DeCoBackbone=LLaVA-1.52026.05 | 26.1 | |
| ICDBackbone=LLaVA-1.52026.05 | 25.9 | |
| VCDBackbone=Qwen-VL2026.05 | 24.6 | |
| ICDBackbone=Qwen-VL2026.05 | 21.7 |