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

Response Classification on BeaverTails V Text-Image Response

84.02F1 Score

GuardReasoner-8B

55.919263.214670.5177.8054Dec 29, 2025
Updated 3d ago

Evaluation Results

MethodLinks
84.02
83.1
82.35
81.73
81.13
80.72
80.44
79.83
79.19
77.85
74.62
73.51
73.39
2025.12
72.92
72.59
72.4
70.91
69.49
66.62
66.13
2025.12
63.5
62.8
57