Object presence hallucination evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.3Accuracy
15
Feb 26, 2026
85.63Accuracy
15
Feb 26, 2026
80.13Accuracy
11
Feb 26, 2026
73.07Accuracy
8
Feb 26, 2026
78Accuracy
8
Feb 26, 2026
88.47Accuracy
8
Feb 26, 2026
88.73Accuracy
8
Feb 26, 2026