Hallucination Detection on HaloQuest benchmark leaderboard · SOTA2 Research

Hallucination Detection on HaloQuest

0.834ROCLogistic

Evaluation Results

Method	Links
Logistic2026.01		0.834	0.84	74.6	85.7	1,874.895	0.114
FaithSCAN2026.01		0.829	0.941	53.2	97.5	1,741.652	1.191
FaithSCAN2026.01		0.827	0.848	76.2	90.2	1,898.95	0.741
Logistic2026.01		0.795	0.887	44.6	91	1,689.458	0.102
SelfCheckGPT2026.01		0.783	0.878	50.1	90.3	2,165.013	367.522
Logistic2026.01		0.735	0.833	85.5	80.7	1,570.349	0.087
P(True)2026.01		0.716	0.761	55.3	73	1,178.084	19.511
FaithSCAN2026.01		0.713	0.854	87	88.5	1,560.237	0.605
SEU2026.01		0.678	0.868	50	91.7	2,199.427	1.821
SEU2026.01		0.66	0.498	77.6	51.5	1,685.975	1.845
EmbVar2026.01		0.641	0.875	44.4	90.2	2,194.586	0.107
P(True)2026.01		0.631	0.776	39.4	83.2	1,143.72	24.299
SE2026.01		0.606	0.873	31.6	87.3	2,019.877	13.812
EmbVar2026.01		0.605	0.521	79	57.8	1,430.884	0.06
SelfCheckGPT2026.01		0.603	0.576	51	53.4	2,588.092	340.683
SE2026.01		0.595	0.28	55.7	27.5	2,632.833	11.212
PE2026.01		0.578	0.526	80.5	53.4	1,326.308	0.002
PE2026.01		0.573	0.726	22.9	78.9	1,328.434	0.002
T-NLL2026.01		0.571	0.55	73	54.9	1,257.512	0.001
EmbVar2026.01		0.546	0.355	51.5	28.4	2,504.584	0.175
T-NLL2026.01		0.542	0.733	25.7	78.4	1,330.996	0.001
SE2026.01		0.537	0.595	80.5	60.8	1,381.929	4.913
SEU2026.01		0.536	0.324	43.4	32.8	2,443.89	1.769
P(True)2026.01		0.515	0.609	77	64.2	1,127.961	14.938
SelfCheckGPT2026.01		0.474	0.623	79.7	63.7	1,602.887	78.613
T-NLL2026.01		0.447	0.372	44.6	37.3	1,524.74	0.001
PE2026.01		0.44	0.368	51.5	34.8	1,491.448	0.002