List your company

Harmfulness Evaluation on Harmfulness Evaluation Suite (JBB, SR, WJ, GCG, JBC, PAIR) (test)

91JBBNo train
-3.6420.9345.570.07Apr 21, 2026

Evaluation results

MethodLinks
No trainBackbone=s1-14B, Dataset Size=-, Temperature=0.02026.049187.291.6839095.389.7
No trainBackbone=s1-3B, Dataset Size=-, Temperature=0.02026.049084.494817593.886.4
No trainBackbone=R1-7B, Dataset Size=-, Temperature=0.02026.047873.591.6767796.982.2
SafeChainBackbone=R1-8B, Dataset Size=40K, Temperature=0.02026.047670.683.2585982.871.6
SafeChainBackbone=R1-32B, Dataset Size=40K, Temperature=0.02026.047678.980.8545984.472.2
SafeChainBackbone=s1-3B, Dataset Size=1K, Temperature=0.02026.04767886.8738084.479.7
No trainBackbone=R1-1.5B, Dataset Size=-, Temperature=0.02026.047465.874685681.369.8
No trainBackbone=R1-8B, Dataset Size=-, Temperature=0.02026.04747890.8728898.483.5
SafeChainBackbone=R1-1.5B, Dataset Size=1K, Temperature=0.02026.047356.965.6532864.156.8
No trainBackbone=R1-32B, Dataset Size=-, Temperature=0.02026.047381.291.67475082.5
SafeChainBackbone=R1-32B, Dataset Size=1K, Temperature=0.02026.047377.687.2616793.876.6
SafeChainBackbone=R1-8B, Dataset Size=1K, Temperature=0.02026.047273.588.4607392.276.5
SafeChainBackbone=R1-7B, Dataset Size=40K, Temperature=0.02026.047171.680694981.370.3
No trainBackbone=R1-14B, Dataset Size=-, Temperature=0.02026.047178.990.8706795.378.8
SafeChainBackbone=s1-14B, Dataset Size=1K, Temperature=0.02026.047178.388.4656096.976.6
SafeChainBackbone=R1-14B, Dataset Size=40K, Temperature=0.02026.047071.980664385.969.5
SafeChainBackbone=R1-7B, Dataset Size=1K, Temperature=0.02026.046967.780.8695487.571.3
SafeChainBackbone=R1-14B, Dataset Size=1K, Temperature=0.02026.046976.486.4695589.174.1
SafeChainBackbone=R1-1.5B, Dataset Size=40k, Temperature=0.02026.046062.365.6503776.658.6
S1-ALTBackbone=s1-3B, Dataset Size=1K, Temperature=0.02026.041311.837.671631.319.4
STAR-1Backbone=R1-1.5B, Dataset Size=1K, Temperature=0.02026.041210.952.46031.318.8
STAR-1Backbone=R1-8B, Dataset Size=1K, Temperature=0.02026.04126.7427532.817.6
STAR-1Backbone=R1-14B, Dataset Size=1K, Temperature=0.02026.04124.847.610337.519.1
STAR-1Backbone=R1-32B, Dataset Size=1K, Temperature=0.02026.0411.67.252.310.27.846.322.6
R1-ALTBackbone=R1-7B, Dataset Size=1K, Temperature=0.02026.04106.436.87223.414.3
STAR-1Backbone=R1-7B, Dataset Size=1K, Temperature=0.02026.049952.48742.221.3
DirectRefusalBackbone=R1-14B, Dataset Size=1k, Temperature=0.02026.04911.520.48020.311.5
DirectRefusalBackbone=R1-32B, Dataset Size=1k, Temperature=0.02026.04910.212306.36.7
DirectRefusalBackbone=R1-1.5B, Dataset Size=1k, Temperature=0.02026.04812.56.44014.17.5
DirectRefusalBackbone=R1-8B, Dataset Size=1k, Temperature=0.02026.04713.4186514.110.6
DirectRefusalBackbone=R1-7B, Dataset Size=1k, Temperature=0.02026.04511.514.4504.76.8
R1-ALTBackbone=R1-1.5B, Dataset Size=1K, Temperature=0.02026.0412.614.8107.84.5
S1-ALTBackbone=s1-14B, Dataset Size=1K, Temperature=0.02026.0411.9821314.16.7
R1-ALTBackbone=R1-8B, Dataset Size=1K, Temperature=0.02026.040121.2204.74.8
R1-ALTBackbone=R1-14B, Dataset Size=1K, Temperature=0.02026.0400.6261010.96.4
R1-ALTBackbone=R1-32B, Dataset Size=1K, Temperature=0.02026.0401.913.2106.33.7