Hallucination detection on CALLHOME (test) benchmark leaderboard · SOTA2 Research

Hallucination detection on CALLHOME (test)

11.56Hallucination Rate (%)RAUQ Entropy

Evaluation Results

Method	Links
RAUQ Entropy2026.04		11.56	86	51	60	44	52	0.53
Mean Entropy2026.04		15.83	86	55	55	55	59	0.57
Perplexity2026.04		25.18	79	50	40	64	56	0.54
Logistic Regression2026.04		27.26	80	55	43	74	61	0.57
Logistic Regression2026.04		29.13	79	52	40	74	58	0.55
Logistic Regression2026.04		32.8	76	50	37	77	55	0.52
Random2026.04		50.03	49	22	15	46	—	—
Attention Score2026.04		53.92	46	23	15	51	15	-0.01