Multiple Choice Question Answering on ArabCulture 1.0 (test)
59.6AccuracyQwen2.5-7B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-7BAugmentation=Native CCKG Assertions2026.01 | 59.6 | |
| Gemma2-9B-ITAugmentation=Base2026.01 | 57.3 | |
| Qwen2.5-7BAugmentation=English CCKG Assertions2026.01 | 53.6 | |
| Qwen2.5-7BAugmentation=Mango2026.01 | 52.6 | |
| Qwen2.5-7BAugmentation=Native CCKG Paths2026.01 | 51.1 | |
| Qwen2.5-7B-ITAugmentation=Native CCKG Assertions2026.01 | 50.8 | |
| Qwen2.5-7BAugmentation=Base2026.01 | 49.3 | |
| Gemma2-9B-ITAugmentation=Native CCKG Paths2026.01 | 49.3 | |
| Qwen2.5-7B-ITAugmentation=English CCKG Paths2026.01 | 49.3 | |
| Llama3.1-8B-ITAugmentation=Base2026.01 | 49.3 | |
| Qwen2.5-7B-ITAugmentation=Native CCKG Paths2026.01 | 49.2 | |
| Qwen2.5-7B-ITAugmentation=Base2026.01 | 48.7 | |
| Qwen2.5-1.5BAugmentation=Native CCKG Assertions2026.01 | 48.3 | |
| Qwen2.5-7B-ITAugmentation=English CCKG Assertions2026.01 | 47.8 | |
| Gemma2-9B-ITAugmentation=Mango2026.01 | 47 | |
| Gemma2-9B-ITAugmentation=English CCKG Paths2026.01 | 46.8 | |
| Qwen2.5-7BAugmentation=English CCKG Paths2026.01 | 46.5 | |
| Qwen2.5-7B-ITAugmentation=Mango2026.01 | 46.5 | |
| Qwen2.5-3BAugmentation=Native CCKG Assertions2026.01 | 45.7 | |
| Qwen2.5-1.5BAugmentation=English CCKG Assertions2026.01 | 45.2 | |
| Qwen2.5-3BAugmentation=English CCKG Assertions2026.01 | 44.6 | |
| Gemma2-9B-ITAugmentation=English CCKG Assertions2026.01 | 43.7 | |
| Qwen2.5-1.5BAugmentation=Mango2026.01 | 43.5 | |
| Qwen2.5-1.5BAugmentation=CoT2026.01 | 43.4 | |
| Gemma2-9B-ITAugmentation=Native CCKG Assertions2026.01 | 42.9 | |
| Qwen2.5-1.5BAugmentation=Native CCKG Paths2026.01 | 42.7 | |
| Qwen2.5-1.5BAugmentation=English CCKG Paths2026.01 | 41.4 | |
| Qwen2.5-3BAugmentation=Mango2026.01 | 40.6 | |
| Qwen2.5-7BAugmentation=CoT2026.01 | 40.6 | |
| Llama3.1-8B-ITAugmentation=English CCKG Paths2026.01 | 40.1 | |
| Qwen2.5-3BAugmentation=English CCKG Paths2026.01 | 39.8 | |
| Qwen2.5-1.5BAugmentation=Base2026.01 | 39.4 | |
| Llama3.1-8B-ITAugmentation=Native CCKG Paths2026.01 | 39.3 | |
| Qwen2.5-3BAugmentation=Native CCKG Paths2026.01 | 38.1 | |
| Qwen2.5-3BAugmentation=Base2026.01 | 37.5 | |
| Llama3.2-3BAugmentation=CoT2026.01 | 37.3 | |
| Llama3.1-8B-ITAugmentation=Native CCKG Assertions2026.01 | 37.2 | |
| Llama3.1-8B-ITAugmentation=English CCKG Assertions2026.01 | 37 | |
| Llama3.1-8BAugmentation=Native CCKG Assertions2026.01 | 35.4 | |
| Llama3.1-8B-ITAugmentation=Mango2026.01 | 35.4 | |
| Llama3.1-8BAugmentation=CoT2026.01 | 35.3 | |
| Qwen2.5-3BAugmentation=CoT2026.01 | 35.2 | |
| Llama3.1-8BAugmentation=Base2026.01 | 34.9 | |
| Llama3.1-8BAugmentation=English CCKG Assertions2026.01 | 34.8 | |
| Llama3.1-8BAugmentation=Native CCKG Paths2026.01 | 34.7 | |
| Gemma2-2BAugmentation=Native CCKG Assertions2026.01 | 34.6 | |
| Gemma2-9BAugmentation=Base2026.01 | 34.5 | |
| Llama3.1-8BAugmentation=Mango2026.01 | 34.5 | |
| Llama3.2-3BAugmentation=Native CCKG Assertions2026.01 | 34.4 | |
| Llama3.1-8B-ITAugmentation=CoT2026.01 | 34.4 | |
| Qwen2.5-0.5BAugmentation=Mango2026.01 | 34.3 | |
| Gemma2-2BAugmentation=Base2026.01 | 34.3 | |
| Gemma2-2BAugmentation=CoT2026.01 | 34.3 | |
| Gemma2-2BAugmentation=Mango2026.01 | 34.3 | |
| Gemma2-9BAugmentation=CoT2026.01 | 34.3 | |
| Gemma2-9BAugmentation=Mango2026.01 | 34.3 | |
| Gemma2-9BAugmentation=English CCKG Assertions2026.01 | 34.3 | |
| Gemma2-9BAugmentation=English CCKG Paths2026.01 | 34.3 | |
| Gemma2-9BAugmentation=Native CCKG Assertions2026.01 | 34.3 | |
| Gemma2-9BAugmentation=Native CCKG Paths2026.01 | 34.3 | |
| Gemma2-9B-ITAugmentation=CoT2026.01 | 34.3 | |
| Qwen2.5-0.5BAugmentation=CoT2026.01 | 34.2 | |
| Qwen2.5-0.5BAugmentation=Native CCKG Assertions2026.01 | 34.2 | |
| Qwen2.5-0.5BAugmentation=Native CCKG Paths2026.01 | 34.2 | |
| Gemma2-2BAugmentation=English CCKG Assertions2026.01 | 34.2 | |
| Llama3.1-8BAugmentation=English CCKG Paths2026.01 | 34.2 | |
| Qwen2.5-7B-ITAugmentation=CoT2026.01 | 34.2 | |
| Gemma2-2BAugmentation=English CCKG Paths2026.01 | 34 | |
| Gemma2-2BAugmentation=Native CCKG Paths2026.01 | 34 | |
| Llama3.2-3BAugmentation=Mango2026.01 | 34 | |
| Llama3.2-3BAugmentation=English CCKG Assertions2026.01 | 34 | |
| Llama3.2-1BAugmentation=Base2026.01 | 33.9 | |
| Qwen2.5-0.5BAugmentation=English CCKG Assertions2026.01 | 33.8 | |
| Qwen2.5-0.5BAugmentation=English CCKG Paths2026.01 | 33.8 | |
| Llama3.2-1BAugmentation=CoT2026.01 | 33.8 | |
| Llama3.2-1BAugmentation=English CCKG Assertions2026.01 | 33.8 | |
| Llama3.2-1BAugmentation=English CCKG Paths2026.01 | 33.8 | |
| Llama3.2-1BAugmentation=Native CCKG Assertions2026.01 | 33.8 | |
| Llama3.2-1BAugmentation=Mango2026.01 | 33.7 | |
| Llama3.2-1BAugmentation=Native CCKG Paths2026.01 | 33.4 | |
| Qwen2.5-0.5BAugmentation=Base2026.01 | 33.3 | |
| Llama3.2-3BAugmentation=Base2026.01 | 33.3 | |
| Llama3.2-3BAugmentation=English CCKG Paths2026.01 | 33 | |
| Llama3.2-3BAugmentation=Native CCKG Paths2026.01 | 31.9 |