List your company

Comprehensive Multimodal Benchmarking on MMBench MMB-EN_en

65.89AccuracyGRIP+decoder+rl
54.366857.358460.3563.3416May 13, 2026

Evaluation results

MethodLinks
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0565.89
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0565.46
OriginalBackbone=LLaVA-1.5-7B, Token Budget=Full2026.0564.09
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0564.09
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0563.75
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0563.75
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0563.66
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0563.32
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0563.14
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0562.97
DARTBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0562.88
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0562.8
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0562.71
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0562.46
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0562.46
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0562.37
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0562.29
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0562.2
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0561.94
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0561.69
DARTBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0561.6
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0561.6
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0561.6
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0560.22
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0560.05
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0559.88
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0559.79
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0559.62
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0559.54
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0559.45
DARTBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0554.81