List your company

Safety Evaluation on HEx-PHI (Score)

69.87Safety Score (HEx-PHI)TOSS
49.205254.570159.93565.2999Mar 1, 2026

Evaluation results

MethodLinks
TOSSModel=Llama-3.2-1B-Instruct2026.0369.87
TOSSModel=Llama-3.2-3B-Instruct2026.0366.89
DSIRModel=Llama-3.2-1B-Instruct2026.0366.08
SafeInstrModel=Llama-3.2-1B-Instruct2026.0365.68
SEALModel=Llama-3.2-1B-Instruct2026.0360.39
SafeInstrModel=Llama-3.2-3B-Instruct2026.0359.34
DSIRModel=Llama-3.2-3B-Instruct2026.0352.63
SEALModel=Llama-3.2-3B-Instruct2026.0351.39
Standard SFTModel=Llama-3.2-1B-Instruct2026.0350
Standard SFTModel=Llama-3.2-3B-Instruct2026.0350