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

Object Hallucination Evaluation on MME Existence (test)

96.67Accuracy

LogicCheckGPT

63.733272.284180.83589.3859Feb 18, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.02
96.6793.33
2024.02
96.6793.33
2024.02
96.6793.33
2024.02
96.6793.33
2024.02
9590
2024.02
93.3386.67
2024.02
93.3386.67
2024.02
9080
2024.02
88.3380
2024.02
86.6773.33
2024.02
8573.33
2024.02
8570
2024.02
83.3366.67
2024.02
83.3366.67
2024.02
8060
2024.02
8060
2024.02
78.3356.67
2024.02
6535