Toxicity and Harmful Content Detection on AgentHarm
94.69Score
JT-Safe-V2-35B
Updated 8d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 94.69 | |
2026.05 | 94.62 | |
2026.05 | 92.77 | |
2026.05 | 90 | |
2026.05 | 84.23 |
JT-Safe-V2-35B
| Method | Links | |
|---|---|---|
2026.05 | 94.69 | |
2026.05 | 94.62 | |
2026.05 | 92.77 | |
2026.05 | 90 | |
2026.05 | 84.23 |