Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Grounding on RefCOCO (test)
Loading...
58.3
Accuracy
LLaVA
-1.2504
14.2098
29.67
45.1302
Feb 3, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
LLaVA
Avg Tokens=576
2026.02
58.3
Pooling
Avg Tokens=128
2026.02
23.01
Pooling
Avg Tokens=64
2026.02
12.01
FastV
Avg Tokens=128
2026.02
10.34
SparseVLM
Avg Tokens=128
2026.02
6.27
VisionZip
Avg Tokens=128
2026.02
4.49
VisionZip
Avg Tokens=64
2026.02
4.04
FastV
Avg Tokens=64
2026.02
2.73
SparseVLM
Avg Tokens=64
2026.02
1.04
Feedback
Search any
task
Search any
task