Machine-Generated Text Detection on RAID 1.0 (test) benchmark leaderboard · SOTA2 Research

Machine-Generated Text Detection on RAID 1.0 (test)

99.44AUROC (ChatGPT)WAVEDETECT-ALL

Evaluation Results

Method	Links
WAVEDETECT-ALL2026.06		99.44	95.97	99.53	99.24	94.62	97.37	99.57	96.38	99.31	96.01	98.95	97.85	71.41	37.53	67.51	59.37	44.66	54.04	67.09	40.54	65.12	36.43	58.03	54.7
Binoculars2026.06		94.83	78.03	94.73	90.47	88.13	92.13	94.19	69.62	90.08	57.51	75.82	84.14	48.38	30.94	54.7	32.12	16.67	38.54	22.57	22.56	44.68	19.79	32.84	35.84
WAVEDETECT-BASE2026.06		89.86	75.48	92.65	86.96	84.15	88.36	89.29	73.13	89.66	65.28	84.6	83.59	7.43	3.66	26.42	2.83	3.54	10.03	3.92	2.38	9.71	1.35	14.88	7.83
RADAR2026.06		89.68	78.81	87.5	86.61	75.16	83.75	87.77	71.85	88.23	75.89	85.18	82.77	0.6	0.78	3.12	0.25	0.1	1.05	0.29	0.27	0.94	0.79	1.93	0.92
Fast-DetectGPT2026.06		87.15	77.35	85.78	80.14	80.6	82.77	86.53	65.13	80.23	53.91	63.69	76.66	0.51	0.45	0.47	0.38	0.36	0.41	0.54	0.31	0.43	0.28	0.26	0.4
RepreGuard2026.06		81.84	55.01	57.58	78.44	56.81	65.25	85.38	55.1	76.91	43.95	65.28	65.6	6.87	1.92	1.45	6.19	1.19	1.9	9.71	1.3	5.39	1.2	1.08	3.47
FourierGPT2026.06		74.54	80.35	83.79	78.54	68.85	74.1	78.55	75.37	71.1	84.16	77.64	77	1.01	9.76	2.16	0.96	0.13	0.21	1.23	4.96	0.13	8.59	0.15	2.66
RoBERTa2026.06		68.25	61.44	59.85	59.54	54.49	65.29	69.55	52.67	69.21	44	57.72	60.18	5.72	3.85	1.11	1.85	0.8	6.14	6.71	1.75	12.4	1.27	7.91	4.5