List your company

Safety Evaluation Suite

Benchmarks

TaskDatasetSOTA resultTrendResults
Safety Evaluation Suite HarmBench, StrongReject, WildJailbreak, XSTest
68.44HarmBench Score
28
Safety Evaluation Suite (Salad-Bench, WildJailbreak, JailbreakBench, WildChat, WildGuard)
100Safety Rate (S.R.)
24
Safety Evaluation Suite (AEG, AEG2, HB-A, HB-V, OAI, SAL, SST, Toxic, WGT, WJB)
89.8AEG Score
18
Safety Evaluation Suite
0.911Score
9