Cultural Safety and Knowledge Evaluation on AdaCultureSafe China
90.45AccuracyQwen2.5-7B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen2.5-7BModel Series=Qwen 2.5, Parameters=7B2026.03 | 90.45 | 59.72 | 69.13 | 0.19 | 0.01 | |
| Llama3.1-8BModel Series=Llama 3.1, Parameters=8B2026.03 | 87.44 | 51.75 | 61.78 | 0.15 | 0.04 | |
| Mistral-7BModel Series=Mistral, Parameters=7B2026.03 | 82.81 | 51.62 | 60.42 | 0.15 | 0.03 |