Add results file for Qwen2.5-72B-Instruct

results/Qwen/Qwen2.5-72B-Instruct_results_2025-05-12_10-34-19.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 8.66595744680851,
+    "speed": 3.401020249078261,
+    "contamination_score": 0,
+    "execution_time": 6340.744371,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 10.0,
+        "count": 6
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 10.0,
+        "count": 9
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 10.0,
+        "count": 17
+      },
+      {
+        "category": "Coding",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 9.6,
+        "count": 5
+      },
+      {
+        "category": "MMLU",
+        "average_score": 9.421487603305785,
+        "count": 121
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 9.333333333333334,
+        "count": 30
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 9.333333333333334,
+        "count": 3
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 9.142857142857142,
+        "count": 7
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 8.968253968253968,
+        "count": 63
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 8.666666666666666,
+        "count": 6
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.375,
+        "count": 8
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 8.365853658536585,
+        "count": 41
+      },
+      {
+        "category": "Structuring",
+        "average_score": 8.333333333333334,
+        "count": 3
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 8.0,
+        "count": 12
+      },
+      {
+        "category": "Long Context",
+        "average_score": 8.0,
+        "count": 4
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 7.818181818181818,
+        "count": 11
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 7.767441860465116,
+        "count": 43
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 7.545454545454546,
+        "count": 22
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 7.083333333333333,
+        "count": 36
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 6.588235294117647,
+        "count": 17
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Short Answer",
+        "average_score": 10.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 9.139737991266376,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 8.201754385964913,
+        "count": 228
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 7.5,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "Qwen/Qwen2.5-72B-Instruct",
+    "model_sha": "495f39366efef23836d0cfae4fbe635880d2be31",
+    "submitted_time": "2025-05-12T08:34:59Z",
+    "likes": 816,
+    "params": 72.706,
+    "license": "other",
+    "model_source": "Hugging Face",
+    "model_category": "Large"
+  }
+}