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

Discriminative Object Hallucination on AMBER Discriminative Task

87.4F1 Score

GPT-4V

70.44874.84979.2583.651Apr 28, 2026May 2, 2026May 6, 2026May 11, 2026May 15, 2026May 19, 2026May 24, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
87.483.4
2026.05
86.5-
2026.05
86.180.8
2026.05
86.178.6
2026.05
85.477
2026.05
84.679.5
2026.05
84.576.8
2026.05
84.479.3
2026.04
82.776.7
2026.04
82.677.8
2026.04
82.176.6
2026.05
81.977.7
2026.05
81.6-
2026.04
79.774
2026.04
75.969.6
2026.04
75.666.3
2026.05
7572.6
2026.05
74.772
2026.04
74.668.2
2026.04
72.869.9
2026.04
7269.2
2026.04
71.167.3