Prompt Classification on SEval
92.5F1 ScoreYuFeng-XGuard
Evaluation Results
| Method | Links | |
|---|---|---|
| YuFeng-XGuardModel Size=8B2026.01 | 92.5 | |
| YuFeng-XGuardModel Size=0.6B2026.01 | 91.7 | |
| Qwen3Guard-GenModel Size=4B, Evaluation protocol=strict2026.01 | 87 | |
| Qwen3Guard-GenModel Size=8B, Evaluation protocol=strict2026.01 | 86.6 | |
| PolyGuardModel Size=7B2026.01 | 86.3 | |
| GPT-OSS-SafeGuardModel Size=20B2026.01 | 85.4 | |
| Qwen3Guard-GenModel Size=0.6B, Evaluation protocol=strict2026.01 | 85.1 | |
| NemotronReasoningModel Size=4B2026.01 | 83.5 | |
| WildGuardModel Size=7B2026.01 | 79.8 | |
| NemotronGuardV2Model Size=8B2026.01 | 77.7 | |
| Qwen3Guard-GenModel Size=0.6B, Evaluation protocol=loose2026.01 | 74.6 | |
| Qwen3Guard-GenModel Size=4B, Evaluation protocol=loose2026.01 | 73.2 | |
| Qwen3Guard-GenModel Size=8B, Evaluation protocol=loose2026.01 | 72.7 | |
| Llama3GuardModel Size=8B2026.01 | 68 | |
| Llama4GuardModel Size=12B2026.01 | 60.4 | |
| ShieldGemmaModel Size=9B2026.01 | 57.1 |