Cultural Safety and Knowledge Evaluation on AdaCultureSafe Afghanistan 1.0
90.4AccuracyQwen2.5-7B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen2.5-7BModel Series=Qwen 2.5, Parameters=7B2026.03 | 90.4 | 50.55 | 62.56 | 0.06 | 0.36 | |
| Llama3.1-8BModel Series=Llama 3.1, Parameters=8B2026.03 | 88.2 | 56.74 | 65.6 | 0.11 | 0.1 | |
| Mistral-7BModel Series=Mistral, Parameters=7B2026.03 | 80.27 | 44.71 | 54.74 | 0.03 | 0.7 |