Prompt Classification

Benchmarks

Dataset Name	SOTA Method	Metric
Aegis	Stage3-DPO	F1 Score91.5	54	17d ago
SimpST	PolyGuard	F1 Score100	44	17d ago
Aegis 2.0	HaloGuard 1.0	F1 Score89.2	42	22d ago
SEA-SafeguardBench	SEA-Guard-12B	AUPRC (Average)93.6	29	4mo ago
EXPGUARD (test)	ShieldGemma	Financial Performance Score0	28	4mo ago
ToxiC	HaloGuard 1.0	F1 Score84.5	26	22d ago
SEA-SafeguardBench English	SEA-Guard-12B	AUPRC98.9	18	4mo ago
XSTest	WildGuard	F1 Score94.8	16	4mo ago
WildG	Qwen3Guard-Gen	F1 Score88.5	16	4mo ago
SorryB	PolyGuard	F1 Score97.2	16	4mo ago
SEval	YuFeng-XGuard	F1 Score92.5	16	4mo ago
OverR	YuFeng-XGuard	F1 Score41.9	16	4mo ago
OpenAIM	Qwen3Guard-Gen	F181.1	16	4mo ago
XSTest Text Prompt	GuardReasoner-8B	F1 Score93.71	14	4mo ago
WildGuard Text Prompt	GuardReasonerVL-7B	F1 Score90.46	14	4mo ago
ToxicChat Text Prompt	GPT4o-mini	F1 Score96.27	14	4mo ago
Simple SafetyTest Text Prompt	Gemini2.5-Flash	F1 Score100	14	4mo ago
OpenAI Moderation Text Prompt		F1 Score88.89	14	4mo ago
Aegis Text Prompt 2.0	GPT4o-mini	F1 Score83.52	14	4mo ago
HarmBench Text Prompt		F1 Score98.85	14	4mo ago
SEALS (SEA)	SEA-Guard-12B	AUPRC96.9	9	4mo ago
LlavaGuard Image Prompt	GPT4o-mini	F1 Score0.752	7	4mo ago
BeaverTails-V Text-Image Prompt	ProGuard-7B	F1 Score88.36	7	4mo ago

Showing 23 of 23 rows