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

Spatial-relation hallucination detection on R-Bench Instance

77.39Accuracy

RVE

60.188464.654269.1273.5858May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
77.39
2026.05
77.3
2026.05
76.29
2026.05
75.19
2026.05
69.12
2026.05
64.61
2026.05
63.51
2026.05
60.85