Add results file for gpt-4o

results/openai/gpt-4o_results_2025-05-11_16-03-16.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 9.019148936170213,
+    "speed": 15.2136124607292,
+    "contamination_score": 0.007696660916347464,
+    "execution_time": 1054.581878,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Hallucination",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Long Context",
+        "average_score": 10.0,
+        "count": 4
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 10.0,
+        "count": 9
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 10.0,
+        "count": 17
+      },
+      {
+        "category": "Paraphrasing",
+        "average_score": 9.833333333333334,
+        "count": 6
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 9.666666666666666,
+        "count": 30
+      },
+      {
+        "category": "Coding",
+        "average_score": 9.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 9.604651162790697,
+        "count": 43
+      },
+      {
+        "category": "MMLU",
+        "average_score": 9.50413223140496,
+        "count": 121
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 9.444444444444445,
+        "count": 63
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 9.4,
+        "count": 5
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 9.333333333333334,
+        "count": 3
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 9.285714285714286,
+        "count": 7
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 9.090909090909092,
+        "count": 11
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 8.705882352941176,
+        "count": 17
+      },
+      {
+        "category": "Structuring",
+        "average_score": 8.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 8.545454545454545,
+        "count": 22
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 8.5,
+        "count": 6
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 8.5,
+        "count": 12
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 8.38888888888889,
+        "count": 36
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.375,
+        "count": 8
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 6.073170731707317,
+        "count": 41
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 10.0,
+        "count": 8
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 10.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 9.532751091703057,
+        "count": 229
+      },
+      {
+        "format": "Generation",
+        "average_score": 8.447368421052632,
+        "count": 228
+      }
+    ]
+  },
+  "config": {
+    "model": "openai/gpt-4o",
+    "model_sha": "na",
+    "submitted_time": "2025-05-11 15:45:37",
+    "likes": -1,
+    "params": 999,
+    "license": "closed",
+    "model_source": "API",
+    "model_category": "Large"
+  }
+}