Visual Question Answering on MMBench Chinese
55.6AccuracyLLaVA-1.5-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaVA-1.5-7BBackbone=LLaVA-1.5-7B, Visual Token Budget=5762026.07 | 55.6 | |
| SparseVLMBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 54.4 | |
| FastVBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 53.6 | |
| VisionZipBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 53.5 | |
| AnchorPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 53.2 | |
| DivPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 52.5 | |
| AnchorPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 52 | |
| CDPrunerBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 51.9 | |
| PyramidDropBackbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 51.8 | |
| PruMerge+Backbone=LLaVA-1.5-7B, Visual Token Budget=1282026.07 | 51.4 | |
| VisionZipBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 51.1 | |
| FastVBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 50.3 | |
| AnchorPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=322026.07 | 49.9 | |
| CDPrunerBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 49.8 | |
| PruMerge+Backbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 49.6 | |
| DivPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 49.4 | |
| SparseVLMBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 48.9 | |
| VisionZipBackbone=LLaVA-1.5-7B, Visual Token Budget=322026.07 | 48 | |
| CDPrunerBackbone=LLaVA-1.5-7B, Visual Token Budget=322026.07 | 46 | |
| DivPruneBackbone=LLaVA-1.5-7B, Visual Token Budget=322026.07 | 45.8 | |
| PyramidDropBackbone=LLaVA-1.5-7B, Visual Token Budget=642026.07 | 45.5 | |
| PruMerge+Backbone=LLaVA-1.5-7B, Visual Token Budget=322026.07 | 45.2 |