List your company

Harmfulness Evaluation on HEx-PHI, AdvBench, HarmBench, & JailbreakBench Full

4.95Average Score (Full)RLVR
0.98762.01633.0454.0737Oct 17, 2025

Evaluation results

MethodLinks
RLVR2025.104.95-0.01
RLVR2025.104.95-0.01
SFT2025.104.78-0.03
SFT2025.104.78-0.03
Base2025.101.14-0.01
Base2025.101.14-0.01