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

Jailbreak Attack Success Rate on HEx-PHI (test)

86.67ASR Category 1

CS-DJ

Updated 4d ago

Evaluation Results

Method	Links
CS-DJ 2026.01		86.67	40	60	50	40	50	16.67	3.33	43.33	20	41
Text-DJ 2026.01		86.67	23.33	70	56.67	33.33	53.33	10	13.33	40	26.67	41.33
Text-DJ 2026.01		80	40	86.67	70	40	50	36.67	16.67	43.33	20	48.33
Text-DJ 2026.01		76.67	66.67	83.33	76.67	73.33	63.33	23.33	40	60	40	60.33
Text-DJ 2026.01		70	33.33	70	66.67	53.33	56.67	23.33	13.33	56.67	30	47.33
CS-DJ 2026.01		70	36.67	83.33	70	36.67	43.33	33.33	16.67	46.67	16.67	45.33
Text-DJ 2026.01		70	63.33	90	76.67	70	63.33	23.33	33.33	56.67	43.33	59
Text-DJ 2026.01		60	30	53.33	56.67	30	56.67	26.67	20	63.33	26.67	42.33
CS-DJ 2026.01		33.33	26.67	56.67	43.33	43.33	43.33	23.33	16.67	33.33	23.33	34.33
CS-DJ 2026.01		33.33	53.33	46.67	36.67	73.33	43.33	23.33	43.33	53.33	43.33	45
CS-DJ 2026.01		30	60	53.33	36.67	70	53.33	20	40	40	43.33	44.67
CS-DJ 2026.01		26.67	40	46.67	36.67	23.33	33.33	26.67	3.33	20	16.67	27.33