Add results file for Qwen2.5-3B-Instruct

results/Qwen/Qwen2.5-3B-Instruct_results_2025-05-11_18-41-22.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 5.634042553191489,
+    "speed": 11.274287270003116,
+    "contamination_score": 0,
+    "execution_time": 1572.871045,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 10.0,
+        "count": 6
+      },
+      {
+        "category": "Coding",
+        "average_score": 9.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 9.411764705882353,
+        "count": 17
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 8.88888888888889,
+        "count": 9
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 7.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Summarization",
+        "average_score": 7.625,
+        "count": 8
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 7.6,
+        "count": 5
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 7.0,
+        "count": 7
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 6.633333333333334,
+        "count": 30
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 6.0476190476190474,
+        "count": 63
+      },
+      {
+        "category": "MMLU",
+        "average_score": 5.950413223140496,
+        "count": 121
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 5.7727272727272725,
+        "count": 22
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 5.7560975609756095,
+        "count": 41
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 4.441860465116279,
+        "count": 43
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 4.361111111111111,
+        "count": 36
+      },
+      {
+        "category": "Long Context",
+        "average_score": 3.75,
+        "count": 4
+      },
+      {
+        "category": "Structuring",
+        "average_score": 3.6666666666666665,
+        "count": 3
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 3.25,
+        "count": 12
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 2.6666666666666665,
+        "count": 3
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 2.5,
+        "count": 6
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 2.0,
+        "count": 17
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 1.3636363636363635,
+        "count": 11
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Short Answer",
+        "average_score": 8.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 6.235807860262009,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 5.087719298245614,
+        "count": 228
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 2.5,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "Qwen/Qwen2.5-3B-Instruct",
+    "model_sha": "aa8e72537993ba99e69dfaafa59ed015b17504d1",
+    "submitted_time": "2025-05-11T16:49:37Z",
+    "likes": 254,
+    "params": 3.086,
+    "license": "other",
+    "model_source": "Hugging Face",
+    "model_category": "Small"
+  }
+}