Our new X account is live! Follow @wizwand_team for updates

Safety Evaluation on PS-Bench base setting (test)

18ASR (Hate Speech)

Stateless

Updated 4d ago

Evaluation Results

Method	Links
Stateless 2026.01		18	2	2	4	6	4	13	20	8.63
Stateless 2026.01		19	4	5	8	15	4	27	12	11.75
Mem0 2026.01		20.3	5.8	2.5	8.4	10.5	11.2	22.3	30.6	13.95
LDAgent 2026.01		21.7	8	6.2	8.6	6.1	14.3	27.9	29.4	15.28
Stateless 2026.01		23	1	2	4	7	2	11	22	9
MemOS 2026.01		23.7	11	7.4	12.2	11.3	15.3	28.9	38.4	18.53
Stateless 2026.01		25	5	8	5	30	13	26	4	14.5
MemU 2026.01		25.2	12	7.9	15.1	16.2	16	28.8	43.2	20.55
Amem 2026.01		28.1	10.1	12.5	16.2	29.9	18.7	32.9	18.6	20.88
Mem0 2026.01		29.2	20.4	11.1	16.4	24.2	19.3	35.5	15.2	21.41
Amem 2026.01		29.9	9.7	10.6	17.5	14.2	18.9	36.6	40.4	22.23
LDAgent 2026.01		30.2	13.5	14.3	13.9	31.2	21.2	33.9	25.8	23
Mem0 2026.01		35.9	11.7	11	15	29.3	17.8	32.6	5.8	19.89
Amem 2026.01		35.9	39.8	17.4	22.2	33.9	28	36.1	15.6	28.61
Stateless 2026.01		36	16	11	6	52	22	34	8	23.13
MemOS 2026.01		36.4	29.7	13.6	23	24.4	23.6	41.9	17.2	26.23
MemU 2026.01		36.6	27.2	17.1	27.8	29.2	23.3	43.8	24.2	28.65
Amem 2026.01		38.1	11	15.4	20.1	40.6	21.3	42.2	7.4	24.51
Mem0 2026.01		38.2	17.5	17.3	14.2	52.8	27.3	41.4	5.6	26.79
MemOS 2026.01		38.3	19.9	12.3	16.6	31.7	22.8	36.4	7.4	23.18
MemOS 2026.01		40.3	21.8	18.4	17.8	47.2	31	45.7	7.6	28.73
MemU 2026.01		40.6	16.8	14.5	20.2	38.7	21.3	38	9.2	24.91
MemOS 2026.01		40.8	13.5	19	26.1	41.9	30.5	47.6	5.2	28.08
LDAgent 2026.01		40.9	30.8	19.9	23	37.6	28.1	46.1	21	30.93
Mem0 2026.01		41	14.3	20.1	23.7	39.4	23.9	44.4	9.8	27.08
LDAgent 2026.01		41.8	17.2	19.1	23.2	41.4	30.9	46.6	8.2	28.55
MemU 2026.01		41.9	14.7	18	25.3	45.3	30.3	50.7	8.4	29.33
MemU 2026.01		42.2	16.6	19.6	18	51.6	29.2	43.3	7.2	28.46
LDAgent 2026.01		44.2	20.3	17.9	16.9	48.5	27.6	42.2	6.8	28.05
Amem 2026.01		44.9	19.4	19.1	19.3	50.3	30.4	44.5	9.4	29.66