Action-relation hallucination evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.25Accuracy
25
May 13, 2026
75.86Accuracy
25
May 13, 2026
83.5Accuracy
25
May 13, 2026
75.23Accuracy
25
May 13, 2026
78.56Accuracy
25
May 13, 2026