Safety Evaluation on RedTeam
96Safety ScoreARES (Qwen)
Evaluation Results
| Method | Links | |
|---|---|---|
| ARES (Qwen)Training Configuration=Ours (Qwen)2026.04 | 96 | |
| ARES (Ministral)Training Configuration=Ours (Ministral)2026.04 | 95 | |
| General Safe-RLHFTraining Configuration=General Safe-RLHF2026.04 | 67 | |
| Initial RLHFTraining Configuration=Initial RLHF2026.04 | 28 | |
| Original ModelTraining Configuration=Original Model2026.04 | 27 |