Add results file for gpt-4.1-mini

results/openai/gpt-4.1-mini_results_2025-05-11_08-48-33.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 8.77659574468085,
+    "speed": 12.59830004953974,
+    "contamination_score": 0,
+    "execution_time": 1313.828051,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 10.0,
+        "count": 6
+      },
+      {
+        "category": "Coding",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 10.0,
+        "count": 9
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 10.0,
+        "count": 17
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 9.6,
+        "count": 5
+      },
+      {
+        "category": "MMLU",
+        "average_score": 9.338842975206612,
+        "count": 121
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 9.19047619047619,
+        "count": 63
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 8.766666666666667,
+        "count": 30
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 8.75,
+        "count": 12
+      },
+      {
+        "category": "Long Context",
+        "average_score": 8.75,
+        "count": 4
+      },
+      {
+        "category": "Structuring",
+        "average_score": 8.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 8.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 8.581395348837209,
+        "count": 43
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 8.166666666666666,
+        "count": 6
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 8.142857142857142,
+        "count": 7
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.125,
+        "count": 8
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 8.0,
+        "count": 22
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 7.975609756097561,
+        "count": 41
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 7.764705882352941,
+        "count": 17
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 7.636363636363637,
+        "count": 11
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 7.611111111111111,
+        "count": 36
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Short Answer",
+        "average_score": 10.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 9.222707423580786,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 8.346491228070175,
+        "count": 228
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 7.5,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "openai/gpt-4.1-mini",
+    "model_sha": "na",
+    "submitted_time": "2025-05-11 08:26:34",
+    "likes": -1,
+    "params": 999,
+    "license": "closed",
+    "model_source": "API",
+    "model_category": "Large"
+  }
+}