Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Object Hallucination Evaluation on A-OKVQA POPE (Random)

89.5Accuracy

HDD

59.724867.454975.18582.9151Dec 22, 2025Dec 24, 2025Dec 27, 2025Dec 30, 2025Jan 1, 2026Jan 4, 2026Jan 7, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.12
89.5--89.4
2025.12
89.5--89.6
2025.12
89--89.4
2025.12
89--88.2
2025.12
88.9485.32-89.21
2025.12
88.6783.63-89.38
2025.12
88.4--87.7
2025.12
88.4--88.5
2025.12
88.3391.46-88.31
2025.12
88.3--88.4
2025.12
88.2--87.4
2025.12
88.1392.06-87.55
2025.12
87.989.16-87.58
2025.12
87.8790.06-87.53
2025.12
87.7392.49-87.01
2025.12
87.6--87.7
2025.12
87.484.67-88.02
2025.12
87.4--88
2025.12
87.2--88.2
2025.12
87.1383.92-87.71
2025.12
86.6--85.3
2025.12
86.3--87.4
2025.12
86.3--87.2
2025.12
86.2790.66-85.48
2025.12
86.1780.84-87.27
2025.12
85.7--86.9
2025.12
85.4381.77-86.23
2025.12
85.1779.79-86.4
2025.12
84.6779.25-85.97
2025.12
84.280.9-85
2025.12
83.8378.05-85.34
2025.12
81.976.63-83.53
2025.12
80.6376.82-81.92
2026.01
61.8363.1355.659.13
2026.01
61.863.2756.2759.56
2026.01
60.8762.7953.3357.68