Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Multimodal Understanding on Combined 9 Benchmarks
Loading...
100
Average Accuracy
LLaVA-NeXT Vanilla 13B
91.056
93.378
95.7
98.022
Aug 25, 2025
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
LLaVA-NeXT Vanilla 13B
Token Budget=2880
2025.08
100
VisionZip ✨
Token Budget=640
2025.08
98.8
MMTok
Token Budget=640
2025.08
98.2
VisionZip ✨
Token Budget=320
2025.08
97.8
VisionZip
Token Budget=640
2025.08
97.7
DivPrune
Token Budget=640
2025.08
97.1
MMTok
Token Budget=320
2025.08
96.4
MMTok
Token Budget=160
2025.08
95.1
VisionZip
Token Budget=320
2025.08
94.7
VisionZip ✨
Token Budget=160
2025.08
94.6
DivPrune
Token Budget=320
2025.08
94.5
DivPrune
Token Budget=160
2025.08
92
VisionZip
Token Budget=160
2025.08
91.4
Feedback
Search any
task
Search any
task