Our new X account is live! Follow @wizwand_team for updates

Multiple Choice Question Answering on ArabCulture 1.0 (test)

59.6Accuracy

Qwen2.5-7B

Updated 3d ago

Evaluation Results

Method	Links
Qwen2.5-7B 2026.01		59.6
Gemma2-9B-IT 2026.01		57.3
Qwen2.5-7B 2026.01		53.6
Qwen2.5-7B 2026.01		52.6
Qwen2.5-7B 2026.01		51.1
Qwen2.5-7B-IT 2026.01		50.8
Qwen2.5-7B 2026.01		49.3
Gemma2-9B-IT 2026.01		49.3
Qwen2.5-7B-IT 2026.01		49.3
Llama3.1-8B-IT 2026.01		49.3
Qwen2.5-7B-IT 2026.01		49.2
Qwen2.5-7B-IT 2026.01		48.7
Qwen2.5-1.5B 2026.01		48.3
Qwen2.5-7B-IT 2026.01		47.8
Gemma2-9B-IT 2026.01		47
Gemma2-9B-IT 2026.01		46.8
Qwen2.5-7B 2026.01		46.5
Qwen2.5-7B-IT 2026.01		46.5
Qwen2.5-3B 2026.01		45.7
Qwen2.5-1.5B 2026.01		45.2
Qwen2.5-3B 2026.01		44.6
Gemma2-9B-IT 2026.01		43.7
Qwen2.5-1.5B 2026.01		43.5
Qwen2.5-1.5B 2026.01		43.4
Gemma2-9B-IT 2026.01		42.9
Qwen2.5-1.5B 2026.01		42.7
Qwen2.5-1.5B 2026.01		41.4
Qwen2.5-3B 2026.01		40.6
Qwen2.5-7B 2026.01		40.6
Llama3.1-8B-IT 2026.01		40.1
Qwen2.5-3B 2026.01		39.8
Qwen2.5-1.5B 2026.01		39.4
Llama3.1-8B-IT 2026.01		39.3
Qwen2.5-3B 2026.01		38.1
Qwen2.5-3B 2026.01		37.5
Llama3.2-3B 2026.01		37.3
Llama3.1-8B-IT 2026.01		37.2
Llama3.1-8B-IT 2026.01		37
Llama3.1-8B 2026.01		35.4
Llama3.1-8B-IT 2026.01		35.4
Llama3.1-8B 2026.01		35.3
Qwen2.5-3B 2026.01		35.2
Llama3.1-8B 2026.01		34.9
Llama3.1-8B 2026.01		34.8
Llama3.1-8B 2026.01		34.7
Gemma2-2B 2026.01		34.6
Gemma2-9B 2026.01		34.5
Llama3.1-8B 2026.01		34.5
Llama3.2-3B 2026.01		34.4
Llama3.1-8B-IT 2026.01		34.4
Qwen2.5-0.5B 2026.01		34.3
Gemma2-2B 2026.01		34.3
Gemma2-2B 2026.01		34.3
Gemma2-2B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B 2026.01		34.3
Gemma2-9B-IT 2026.01		34.3
Qwen2.5-0.5B 2026.01		34.2
Qwen2.5-0.5B 2026.01		34.2
Qwen2.5-0.5B 2026.01		34.2
Gemma2-2B 2026.01		34.2
Llama3.1-8B 2026.01		34.2
Qwen2.5-7B-IT 2026.01		34.2
Gemma2-2B 2026.01		34
Gemma2-2B 2026.01		34
Llama3.2-3B 2026.01		34
Llama3.2-3B 2026.01		34
Llama3.2-1B 2026.01		33.9
Qwen2.5-0.5B 2026.01		33.8
Qwen2.5-0.5B 2026.01		33.8
Llama3.2-1B 2026.01		33.8
Llama3.2-1B 2026.01		33.8
Llama3.2-1B 2026.01		33.8
Llama3.2-1B 2026.01		33.8
Llama3.2-1B 2026.01		33.7
Llama3.2-1B 2026.01		33.4
Qwen2.5-0.5B 2026.01		33.3
Llama3.2-3B 2026.01		33.3
Llama3.2-3B 2026.01		33
Llama3.2-3B 2026.01		31.9