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

Hallucination Evaluation on MME Hallucination

195Existence Score

DAC

Updated 16d ago

Evaluation Results

Method
DAC 2025.02	195	158.33	133.33	170	656.67
AGLA 2026.04	195	153.9	129.4	161.7	640
ACT 2026.04	195	153.3	150	170	668.3
TAME 2026.04	193	137.3	139	164.7	634
ONLY 2026.04	191.7	145.6	136.7	161.7	635.6
CoFi-Dec 2025.12	190.26	144.43	133.71	165.62	627.39
SID 2025.02	190	148.33	128.33	175	641.66
CCA 2025.02	190	148.33	128.33	175	641.66
HALC 2026.04	190	143.3	128.3	160	621.6
CCA 2026.04	190	148.3	128.3	153	641.7
EAH 2026.04	190	108.3	145	160.7	604
VAR 2026.04	190	148.3	138.3	155	631.3
MEMVR 2026.04	190	155	133.3	170.6	648.3
AvISC 2024.05	189.29	104.76	106.19	127.86	528.09
DeFG 2025.12	188.33	142.5	131.33	163.17	625.83
RITUAL 2025.12	187.53	139.58	125	163.33	626.29
Woodpecker 2025.12	187.53	126.25	126.66	149.17	589.58
RITUAL 2026.04	187.5	139.6	125	164.2	616.3
VCD 2025.12	186.67	125.56	128.89	139.45	580.56
M3ID 2025.12	186.67	128.33	131.63	151.67	597.5
DOPRA 2026.04	185.7	138.3	120.7	133	577.7
AvISC 2024.05	184.76	82.85	74.76	131.43	473.8
VCD 2026.04	184.7	137.3	128.7	153	603.7
VCD 2025.02	184.66	138.33	128.67	153	604.66
SID 2026.04	183.9	132.2	127.8	155.9	599.8
OPERA 2025.12	183.33	137.22	122.78	155	598.33
HALC 2025.12	183.33	133.33	109.58	155	581.24
OPERA 2026.04	180.7	133.3	111.7	123.3	549
OPERA 2025.02	180.67	133.33	123.33	155	592.33
Dola 2026.04	180.1	127.4	119.3	154.6	594.1
M3ID 2024.05	178.33	107.22	96.39	127.5	509.44
DoLa 2025.12	176.67	113.33	90.55	141.67	522.22
Baseline 2025.02	175.67	124.67	114	151	565.33
M3ID 2024.05	173.89	89.72	72.72	110.56	446.88
Regular 2025.12	173.75	121.67	117.92	149.17	562.5
Base Decoding 2024.05	173.57	110	100.47	125.24	509.28
VCD 2024.05	172.62	98.33	71.9	117.14	459.99
VCD 2024.05	172.14	117.14	103.33	119.52	512.14
Base Decoding 2024.05	170.19	89.52	67.62	114.76	442.09