Add results file for Llama-3.3-70B-Instruct

results/meta-llama/Llama-3.3-70B-Instruct_results_2025-05-12_11-36-59.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 7.782978723404256,
+    "speed": 3.0692676555320553,
+    "contamination_score": 0,
+    "execution_time": 3509.957817,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 10.0,
+        "count": 6
+      },
+      {
+        "category": "Long Context",
+        "average_score": 9.75,
+        "count": 4
+      },
+      {
+        "category": "Coding",
+        "average_score": 9.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 9.411764705882353,
+        "count": 17
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 9.333333333333334,
+        "count": 3
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 9.0,
+        "count": 5
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 8.857142857142858,
+        "count": 7
+      },
+      {
+        "category": "MMLU",
+        "average_score": 8.84297520661157,
+        "count": 121
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 8.666666666666666,
+        "count": 30
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 8.5,
+        "count": 6
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 8.365079365079366,
+        "count": 63
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 7.777777777777778,
+        "count": 9
+      },
+      {
+        "category": "Summarization",
+        "average_score": 7.5,
+        "count": 8
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 7.097560975609756,
+        "count": 41
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 6.75,
+        "count": 36
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 6.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 6.545454545454546,
+        "count": 11
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 6.2727272727272725,
+        "count": 22
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 6.0,
+        "count": 12
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 5.906976744186046,
+        "count": 43
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 5.647058823529412,
+        "count": 17
+      },
+      {
+        "category": "Structuring",
+        "average_score": 3.6666666666666665,
+        "count": 3
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "MCQ",
+        "average_score": 8.502183406113538,
+        "count": 229
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 8.0,
+        "count": 5
+      },
+      {
+        "format": "Generation",
+        "average_score": 7.1535087719298245,
+        "count": 228
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 5.0,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "meta-llama/Llama-3.3-70B-Instruct",
+    "model_sha": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
+    "submitted_time": "2025-05-12T08:35:39Z",
+    "likes": 2309,
+    "params": 70.554,
+    "license": "llama3.3",
+    "model_source": "Hugging Face",
+    "model_category": "Large"
+  }
+}