{ "results": { "average_score": 7.0638297872340425, "speed": 4.64431529752851, "contamination_score": 0, "execution_time": 5309.071073, "errors": [], "scores_by_category": [ { "category": "Paraphrasing", "average_score": 10.0, "count": 6 }, { "category": "Sentiment Analysis", "average_score": 10.0, "count": 9 }, { "category": "Coding", "average_score": 10.0, "count": 3 }, { "category": "Reading Comprehension", "average_score": 10.0, "count": 17 }, { "category": "General Knowledge", "average_score": 8.492063492063492, "count": 63 }, { "category": "MMLU", "average_score": 8.429752066115702, "count": 121 }, { "category": "Summarization", "average_score": 8.125, "count": 8 }, { "category": "Dialect Detection", "average_score": 8.0, "count": 11 }, { "category": "Long Context", "average_score": 7.75, "count": 4 }, { "category": "Trust & Safety", "average_score": 6.966666666666667, "count": 30 }, { "category": "Function Calling", "average_score": 6.666666666666667, "count": 3 }, { "category": "Reasoning & Math", "average_score": 6.255813953488372, "count": 43 }, { "category": "Diacritization", "average_score": 6.25, "count": 12 }, { "category": "RAG QA", "average_score": 5.878048780487805, "count": 41 }, { "category": "Entity Extraction", "average_score": 5.4, "count": 5 }, { "category": "Writing (incl Dialects)", "average_score": 5.136363636363637, "count": 22 }, { "category": "Instruction Following", "average_score": 5.0, "count": 7 }, { "category": "Translation (incl Dialects)", "average_score": 4.388888888888889, "count": 36 }, { "category": "Hallucination", "average_score": 4.333333333333333, "count": 3 }, { "category": "Arabic Language & Grammar", "average_score": 3.5294117647058822, "count": 17 }, { "category": "Structuring", "average_score": 3.3333333333333335, "count": 3 }, { "category": "Transliteration", "average_score": 0.16666666666666666, "count": 6 } ], "scores_by_format": [ { "format": "Short Answer", "average_score": 10.0, "count": 5 }, { "format": "MCQ", "average_score": 8.174672489082969, "count": 229 }, { "format": "Fill-in-the-blank", "average_score": 7.5, "count": 8 }, { "format": "Generation", "average_score": 5.868421052631579, "count": 228 } ] }, "config": { "model": "QCRI/Fanar-1-9B-Instruct", "model_sha": "8a7f56e2c7e58f70099dcd1f9b4490b1af18f57d", "submitted_time": "2025-06-10T10:13:59Z", "likes": 3, "params": 8.784, "license": "apache-2.0", "model_source": "Hugging Face", "model_category": "Small" } }