Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Reasoning on GQA (test-dev)
Loading...
62
Accuracy
LLaVA-1.5-7B
42.864
47.832
52.8
57.768
Feb 4, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
LLaVA-1.5-7B
Reduction Ratio=0%, Vi...
2026.02
62
Mask-LLaVA
Reduction Ratio=90%, V...
2026.02
60.6
Mask-LLaVA
Reduction Ratio=97%, V...
2026.02
60.5
Voco-LLaMa
Reduction Ratio=88%, V...
2026.02
60.4
M3
Reduction Ratio=75%, V...
2026.02
60.3
Voco-LLaMa
Reduction Ratio=88%, V...
2026.02
60.2
MQT
Reduction Ratio=88%, V...
2026.02
60
Voco-LLaMa
Reduction Ratio=88%, V...
2026.02
59.4
MQT
Reduction Ratio=88%, V...
2026.02
58.8
Mask-LLaVA
Reduction Ratio=97%, V...
2026.02
58.5
M3
Reduction Ratio=75%, V...
2026.02
58
MQT
Reduction Ratio=88%, V...
2026.02
57.6
FasterVLM
Reduction Ratio=90%, V...
2026.02
54.9
LLaVA-1.5-7B (Random Patch Dropping)
Reduction Ratio=90%, V...
2026.02
54.2
FasterVLM
Reduction Ratio=95%, V...
2026.02
51.5
LLaVA-1.5-7B (Random Patch Dropping)
Reduction Ratio=95%, V...
2026.02
51
FitPrune
Reduction Ratio=90%, V...
2026.02
49.9
SparseVLM
Reduction Ratio=90%, V...
2026.02
48.8
FitPrune
Reduction Ratio=95%, V...
2026.02
43.6
Feedback
Search any
task
Search any
task