Add results file for gpt-4.1-nano

results/openai/gpt-4.1-nano_results_2025-04-28_21-12-26.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 8.040860215053764,
+    "speed": 1.8531926430107528,
+    "contamination_score": -0.021933454541668063,
+    "execution_time": 861.734579,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 10.0,
+        "count": 6
+      },
+      {
+        "category": "Coding",
+        "average_score": 10.0,
+        "count": 3
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 9.727272727272727,
+        "count": 22
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 9.523809523809524,
+        "count": 21
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 8.88888888888889,
+        "count": 9
+      },
+      {
+        "category": "Summarization",
+        "average_score": 8.666666666666666,
+        "count": 9
+      },
+      {
+        "category": "MMLU",
+        "average_score": 8.442622950819672,
+        "count": 122
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 8.386363636363637,
+        "count": 44
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 8.0,
+        "count": 7
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 8.0,
+        "count": 12
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 8.0,
+        "count": 5
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 7.865671641791045,
+        "count": 67
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 7.647058823529412,
+        "count": 17
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 7.465116279069767,
+        "count": 43
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 7.166666666666667,
+        "count": 6
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 7.033333333333333,
+        "count": 30
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 7.0,
+        "count": 3
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 6.9411764705882355,
+        "count": 17
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 6.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 5.545454545454546,
+        "count": 11
+      },
+      {
+        "category": "Structuring",
+        "average_score": 4.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Long Context",
+        "average_score": 4.0,
+        "count": 5
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "Generation",
+        "average_score": 8.48165137614679,
+        "count": 218
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 8.0,
+        "count": 5
+      },
+      {
+        "format": "MCQ",
+        "average_score": 7.6923076923076925,
+        "count": 234
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 6.25,
+        "count": 8
+      }
+    ]
+  },
+  "config": {
+    "model": "openai/gpt-4.1-nano",
+    "model_sha": "NA",
+    "submitted_time": "2025-04-28 20:57:22",
+    "likes": -1,
+    "params": 999,
+    "license": "closed",
+    "model_source": "API",
+    "model_category": "Large"
+  }
+}