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

Object Hallucination on POPE Adversarial

90Accuracy

LogicCheckGPT

77.176880.505983.83587.1641Jun 27, 2023Dec 5, 2023May 14, 2024Oct 22, 2024Apr 1, 2025Sep 9, 2025Feb 17, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2024.02
90--89.58--
2024.02
89--88--
2024.02
88.67--88.27--
2023.11
87.9-----
2026.02
87.8-86.487.63--
2023.11
87.7-----
2024.02
87.67--87.54--
2023.11
87.2-----
2026.02
87.13-84.0786.73--
2026.02
87.1-79.8786.09--
2026.02
87.1-79.8786.09--
2026.02
87.03-80.9386.19--
2024.02
87--87.62--
2026.02
86.93-80.1385.98--
2026.02
86.87-81.286.08--
2026.02
86.87-81.286.08--
2026.02
86.87-81.286.08--
2026.02
86.73-79.2785.67--
2024.02
86.67--86.67--
2026.02
86.57-81.685.86--
2023.12
86.5493.0179.5285.7346.33-
2023.11
86.2-----
2026.02
86.13-82.0785.55--
2026.02
86.13-81.8785.52--
2026.01
86.12--84.28--
2023.12
85.9391.7878.9384.8743-
2023.11
85.9-----
2023.11
85.9-----
2026.01
85.86--83.92--
2023.12
85.7792.0178.3384.6242.57-
2024.03
85.6791.9978.1384.542.47-
2024.03
85.6--84.744.1-
2023.11
85.3788.6981.0784.71--
2023.12
85.3385.4385.285.3149.87-
2024.02
85.33--86.25--
2026.02
85.27-80.484.51--
2026.02
85.12--83.08--
2024.03
85.1--84.244-
2023.11
84.3--83.243.5-
2023.12
84.1782.1787.2784.6453.1-
2023.12
84.1285.5482.1383.848-
2026.02
83.96--81.82--
2026.02
83.52--81.38--
2026.02
83.5-83.283.51--
2024.02
83.33--84.84--
2026.02
83.23-78.3382.37--
2026.02
83.2-78.282.32--
2026.02
83.2-78.282.32--
2023.12
83.185.679.682.4946.5-
2023.06
83.185.679.682.4946.5-
2023.11
83.185.679.682.49--
2023.12
83.185.679.682.4946.5-
2023.12
83.185.679.682.4946.5-
2024.03
83.185.679.682.4946.5-
2024.04
83.185.679.682.546.5-
2023.09
83.185.679.682.4946.5-
2026.01
82.94--81.91--
2026.02
82.9--82--
2026.02
82.83--80.82--
2026.01
82.79--80.82--
2026.02
82.68--80.78--
2024.02
82.67--80.59--
2026.02
82.6--81.6--
2026.01
82.57--81.23--
2026.01
82.53--80.56--
2026.02
82.53--80.56--
2024.03
82.4--81.645.2-
2023.12
82.3683.680.538248.18-
2023.12
82.3683.680.538248.18-
2024.02
82--82.23--
2026.02
81.83-78.5381.21--
2026.02
81.77-77.2780.91--
2023.11
81.6--80.845.8-
2026.02
81.6--80.6--
2026.02
81.23-78.9380.79--
2026.02
81.1--80--
2026.02
81.08--80.92--
2023.09
80.9781.8879.5380.6948.57-
2026.02
80.92--79.56--
2024.03
80.8780.9580.7380.84--
2025.12
80.6--82.456.4-
2026.02
80.23--78.74--
2026.01
79.72--78.23--
2026.02
79.68--78.14--
2024.03
79.5679.6779.3979.52--
2026.02
79.56--78.12--
2026.01
79.48--81.86--
2024.12
79.475.5187.180.88--
2026.01
79.37--77.88--
2026.02
79.37--77.88--
2023.12
79.261.1982.9370.4267.77-
2026.01
79.16--81.52--
2026.01
78.82--82.08--
2024.04
78.876.693.784.361.7-
2026.02
78.62--80.62--
2026.02
78.47--81.12--
2026.01
78.34--81.62--
2024.12
77.9772.7989.4380.24--
2026.01
77.92--79.96--
2024.02
77.67--79.14--
Showing 100 of 207 rows