Add results file for Qwen3-8B

results/Qwen/Qwen3-8B_results_2025-05-11_11-50-12.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 6.561702127659575,
+    "speed": 22.56715699295565,
+    "contamination_score": 0,
+    "execution_time": 8076.914609,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 10.0,
+        "count": 9
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 9.428571428571429,
+        "count": 7
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 9.411764705882353,
+        "count": 17
+      },
+      {
+        "category": "Paraphrasing",
+        "average_score": 8.333333333333334,
+        "count": 6
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 8.333333333333334,
+        "count": 3
+      },
+      {
+        "category": "MMLU",
+        "average_score": 8.264462809917354,
+        "count": 121
+      },
+      {
+        "category": "Summarization",
+        "average_score": 7.5,
+        "count": 8
+      },
+      {
+        "category": "Long Context",
+        "average_score": 7.5,
+        "count": 4
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 6.809523809523809,
+        "count": 63
+      },
+      {
+        "category": "Coding",
+        "average_score": 6.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 6.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 6.409090909090909,
+        "count": 22
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 6.333333333333333,
+        "count": 30
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 6.097560975609756,
+        "count": 41
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 5.465116279069767,
+        "count": 43
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 5.0,
+        "count": 5
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 4.888888888888889,
+        "count": 36
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 4.545454545454546,
+        "count": 11
+      },
+      {
+        "category": "Structuring",
+        "average_score": 3.0,
+        "count": 3
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 2.6666666666666665,
+        "count": 6
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 2.176470588235294,
+        "count": 17
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 0.4166666666666667,
+        "count": 12
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Short Answer",
+        "average_score": 10.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 7.77292576419214,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 5.324561403508772,
+        "count": 228
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 5.0,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "Qwen/Qwen3-8B",
+    "model_sha": "2069b3fae1114555f3c020c81410e51fa0f656f2",
+    "submitted_time": "2025-05-11T06:25:11Z",
+    "likes": 262,
+    "params": 8.191,
+    "license": "apache-2.0",
+    "model_source": "Hugging Face",
+    "model_category": "Small"
+  }
+}