List your company

Prompt Harmfulness Classification on WildG

96.2F1 ScoreHaloGuard 1.0
52.62463.93775.2586.563Jul 2, 2026Jul 3, 2026Jul 4, 2026Jul 5, 2026Jul 6, 2026Jul 7, 2026

Evaluation results

MethodLinks
HaloGuard 1.0Size=4B2026.0796.2
HaloGuard 1.0Size=0.8B2026.0795.9
Qwen3Guard-8B-GenParams=8B2026.0789.1
WildGuardSize=7B2026.0788.9
Qwen3Guard-GenSize=8B2026.0788.9
Stage1-SFT-v4Params=4B2026.0788.8
Stage3-DPOParams=4B2026.0788.8
Qwen3Guard-4B-GenParams=4B2026.0788.7
Stage2-SFTParams=4B2026.0788.4
PolyGuard-QwenSize=7B2026.0788.1
YuFeng-XGuard-Reason-0.6BParams=0.6B2026.0787.9
Qwen3Guard-0.8B-GenParams=0.8B2026.0787.8
Qwen3Guard-GenSize=0.6B2026.0787.7
YuFeng-XGuard-Reason-8BParams=8B2026.0787.7
Stage1-SFT-v0Params=4B2026.0787
Stage1-SFT-v1Params=4B2026.0787
Stage1-SFT-v3Params=4B2026.0786.4
Qwen3Guard-GenSize=4B2026.0785.6
Stage1-SFT-v2Params=4B2026.0782.9
NemoGuardSize=8B2026.0781.6
LlamaGuard4Size=12B2026.0773
ShieldGemmaSize=27B2026.0754.3