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

Jailbreaking on AdvBench (test)

99.04Average ASR

CHaRS-PCT

Updated 1mo ago

Evaluation Results

Method	Links
CHaRS-PCT 2026.02		99.04	-	-	-	-	-	-
CHaRS 2026.02		98.08	-	-	-	-	-	-
CHaRS-PCT 2026.02		98.08	-	-	-	-	-	-
CHaRS 2026.02		98.08	-	-	-	-	-	-
ActAdd 2026.02		95.19	-	-	-	-	-	-
CHaRS 2026.02		95.19	-	-	-	-	-	-
CHaRS-PCT 2026.02		95.19	-	-	-	-	-	-
CHaRS 2026.02		95.19	-	-	-	-	-	-
CHaRS 2026.02		95.19	-	-	-	-	-	-
ActAdd 2026.02		94.23	-	-	-	-	-	-
CHaRS-PCT 2026.02		93.27	-	-	-	-	-	-
CHaRS-PCT 2026.02		93.27	-	-	-	-	-	-
ActAdd 2026.02		91.35	-	-	-	-	-	-
ActAdd 2026.02		91.35	-	-	-	-	-	-
ActAdd 2026.02		89.42	-	-	-	-	-	-
CHaRS 2026.02		89.42	-	-	-	-	-	-
CHaRS-PCT 2026.02		88.46	-	-	-	-	-	-
ActAdd 2026.02		82.69	-	-	-	-	-	-
CHaRS 2026.02		79.81	-	-	-	-	-	-
CHaRS-PCT 2026.02		79.81	-	-	-	-	-	-
ActAdd 2026.02		74.04	-	-	-	-	-	-
MTSA-R3 2025.05		63.92	72	66.5	56	50.5	64	74.5
MTSA-R2 2025.05		61.1	68.5	64.5	56.5	47.5	58.5	71
MTSA-R1 2025.05		58.08	64.5	65	54.5	46.5	51	67
RedQueen 2025.05		53.42	63	58.5	53	43.5	45	57.5
COA 2025.05		51	52	63.5	55	24.5	48	63
PAIR 2025.05		48.5	57.5	61	51.5	20.5	39.5	61
ActorAttack 2025.05		43.92	47.5	51.5	44.5	35	41.5	43.5
CodeAttack 2025.05		43.75	44.5	56	38.5	37	43.5	43
CipherChat 2025.05		32.33	41.5	32	28.5	22	38	32
GCG 2025.05		27.17	33.5	12.5	22	34.5	24.5	36
PAP 2025.05		26.91	36	24.5	14.5	26	32.5	28
HarmfulQA 2025.05		26.68	34.5	39	33	16.5	21	16