Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Object Hallucination Detection on nocaps-FOIL (Near-Domain)

92.6AP

EXPERT

65.66472.65779.6586.643May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
92.69398.5
2026.05
88.889.495.1
2026.05
88.49097.9
2026.05
87.588.998.3
2026.05
86.186.898.6
2026.05
7780.795.1
2026.05
76.978.896.3
2026.05
74.277.892.5
2026.05
73.276.990.7
2026.05
73.27792.7
2026.05
72.975.994.9
2026.05
71.974.496.2
2026.05
71.775.197.3
2026.05
70.873.990.3
2026.05
69.872.694.2
2026.05
68.771.887
2026.05
66.7--
2026.05
--93.6