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

Object Hallucination Detection on nocaps FOIL In-Domain

88.8AP

EXPERT

66.12872.01477.983.786May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
88.891.797.6
2026.05
88.590.295.9
2026.05
87.990.797.1
2026.05
85.887.798
2026.05
82.586.696.3
2026.05
74.976.897.1
2026.05
73.57791.4
2026.05
73.377.895.5
2026.05
73.176.598
2026.05
72.876.193.1
2026.05
71.974.790.6
2026.05
71.8--
2026.05
71.476.394.3
2026.05
71.374.689.4
2026.05
7072.994.3
2026.05
6971.887.8
2026.05
677084.1
2026.05
--94.7