Safety Evaluation on DNA
95.9Safety ScoreClaude-3.7-Sonnet
Evaluation results
| Method | Links | |
|---|---|---|
| Claude-3.7-SonnetEvaluation Source=Reproduced2025.01 | 95.9 | |
| Qwen2.5 Instruct (72B)Evaluation Source=Reproduced2025.01 | 95.9 | |
| DeepSeek-V3Evaluation Source=Reproduced, Risk Control System=Enabled2025.01 | 95.6 | |
| DeepSeek-R1Evaluation Source=Reproduced, Chain of Thought=visible, Risk Control System=Enabled2025.01 | 94.8 | |
| DeepSeek-R1Evaluation Source=Reproduced, Chain of Thought=hidden, Risk Control System=Enabled2025.01 | 93.7 | |
| GPT-4o (2024-05-13)Evaluation Source=Reproduced2025.01 | 90.6 | |
| o1 (2024-12-17)Evaluation Source=Reproduced2025.01 | 86.2 |