Add results file for gpt-4o

results/openai/gpt-4o_results_2025-04-28_20-32-11.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 9.498924731182795,
+    "speed": 3.2900419806451615,
+    "contamination_score": -0.006184849300633566,
+    "execution_time": 1529.869521,
+    "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": "RAG QA",
+        "average_score": 10.0,
+        "count": 21
+      },
+      {
+        "category": "Coding",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "MMLU",
+        "average_score": 10.0,
+        "count": 122
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 9.863636363636363,
+        "count": 22
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 9.82089552238806,
+        "count": 67
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 9.666666666666666,
+        "count": 3
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 9.588235294117647,
+        "count": 17
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 9.571428571428571,
+        "count": 7
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 9.534883720930232,
+        "count": 43
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 9.333333333333334,
+        "count": 12
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 9.333333333333334,
+        "count": 30
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 8.636363636363637,
+        "count": 44
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 8.6,
+        "count": 5
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.444444444444445,
+        "count": 9
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 8.333333333333334,
+        "count": 6
+      },
+      {
+        "category": "Structuring",
+        "average_score": 7.0,
+        "count": 3
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 6.454545454545454,
+        "count": 11
+      },
+      {
+        "category": "Long Context",
+        "average_score": 6.0,
+        "count": 5
+      }
+    ],
+    "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": 9.786324786324787,
+        "count": 234
+      },
+      {
+        "format": "Generation",
+        "average_score": 9.160550458715596,
+        "count": 218
+      }
+    ]
+  },
+  "config": {
+    "model": "openai/gpt-4o",
+    "model_sha": "NA",
+    "submitted_time": "2025-04-28 20:04:40",
+    "likes": -1,
+    "params": 999,
+    "license": "closed",
+    "model_source": "API",
+    "model_category": "Large"
+  }
+}