Add results file for gpt-oss-20b

results/openai/gpt-oss-20b_results_2025-08-07_16-30-11.json

@@ -0,0 +1,153 @@
+{
+  "results": {
+    "average_score": 6.368085106382979,
+    "speed": 12.057397403049587,
+    "contamination_score": 0,
+    "execution_time": 9660.708369,
+    "errors": [],
+    "scores_by_category": [
+      {
+        "category": "Paraphrasing",
+        "average_score": 9.833333333333334,
+        "count": 6
+      },
+      {
+        "category": "Reading Comprehension",
+        "average_score": 9.411764705882353,
+        "count": 17
+      },
+      {
+        "category": "Sentiment Analysis",
+        "average_score": 8.88888888888889,
+        "count": 9
+      },
+      {
+        "category": "MMLU",
+        "average_score": 8.512396694214877,
+        "count": 121
+      },
+      {
+        "category": "Trust & Safety",
+        "average_score": 6.666666666666667,
+        "count": 30
+      },
+      {
+        "category": "Coding",
+        "average_score": 6.666666666666667,
+        "count": 3
+      },
+      {
+        "category": "Instruction Following",
+        "average_score": 6.571428571428571,
+        "count": 7
+      },
+      {
+        "category": "General Knowledge",
+        "average_score": 6.507936507936508,
+        "count": 63
+      },
+      {
+        "category": "Structuring",
+        "average_score": 6.333333333333333,
+        "count": 3
+      },
+      {
+        "category": "Reasoning & Math",
+        "average_score": 6.27906976744186,
+        "count": 43
+      },
+      {
+        "category": "Summarization",
+        "average_score": 6.0,
+        "count": 8
+      },
+      {
+        "category": "Transliteration",
+        "average_score": 5.333333333333333,
+        "count": 6
+      },
+      {
+        "category": "Writing (incl Dialects)",
+        "average_score": 5.181818181818182,
+        "count": 22
+      },
+      {
+        "category": "Translation (incl Dialects)",
+        "average_score": 5.166666666666667,
+        "count": 36
+      },
+      {
+        "category": "Long Context",
+        "average_score": 5.0,
+        "count": 4
+      },
+      {
+        "category": "RAG QA",
+        "average_score": 4.317073170731708,
+        "count": 41
+      },
+      {
+        "category": "Entity Extraction",
+        "average_score": 4.2,
+        "count": 5
+      },
+      {
+        "category": "Function Calling",
+        "average_score": 3.6666666666666665,
+        "count": 3
+      },
+      {
+        "category": "Hallucination",
+        "average_score": 3.3333333333333335,
+        "count": 3
+      },
+      {
+        "category": "Arabic Language & Grammar",
+        "average_score": 2.9411764705882355,
+        "count": 17
+      },
+      {
+        "category": "Dialect Detection",
+        "average_score": 2.727272727272727,
+        "count": 11
+      },
+      {
+        "category": "Diacritization",
+        "average_score": 0.0,
+        "count": 12
+      }
+    ],
+    "scores_by_format": [
+      {
+        "format": "MCQ",
+        "average_score": 8.069868995633188,
+        "count": 229
+      },
+      {
+        "format": "Short Answer",
+        "average_score": 8.0,
+        "count": 5
+      },
+      {
+        "format": "Fill-in-the-blank",
+        "average_score": 5.0,
+        "count": 8
+      },
+      {
+        "format": "Generation",
+        "average_score": 4.671052631578948,
+        "count": 228
+      }
+    ]
+  },
+  "config": {
+    "model": "openai/gpt-oss-20b",
+    "model_sha": "2e8f8052ee2aeee907f76e08c08b9fdde8677ca8",
+    "submitted_time": "2025-08-07T08:38:37Z",
+    "likes": 2226,
+    "params": 21.512,
+    "license": "apache-2.0",
+    "model_source": "Hugging Face",
+    "model_category": "Medium"
+  }
+}