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

Object Hallucination on A-OKVQA POPE (test)

90.13Accuracy (Random)

OSGA

83.182884.986486.7988.5936Jan 7, 2026Jan 10, 2026Jan 14, 2026Jan 18, 2026Jan 22, 2026Jan 26, 2026Jan 30, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
90.1389.7585.2785.4379.978.985.184.69------
2026.01
88.2787.5485.1784.7479.3779.9784.2784.08------
2026.01
86.386.0380.9381.5673.9376.14--87.7984.3378.9684.3370.1983.2
2026.01
86.1586.3481.8582.8274.9777.7380.9982.3------
2026.01
85.5785.0681.9381.9577.4378.9981.6482------
2026.01
85.0384.6180.680.9274.976.59--87.0982.2779.6182.2771.7582.13
2026.01
84.0383.2280.2380.0374.2775.34--87.6879.280.8779.272.3378.6
2026.01
83.4582.5679.979.5974.0475.1579.1379.1------