Update benchmark_results.json with Yi-34B benchmark comparison

benchmark_results.json

@@ -126,6 +126,54 @@
           "accuracy": 69.2
         }
       }
+    },
+    {
+      "model": "Yi-34B-Chat",
+      "parameters": "34B",
+      "provider": "01.AI",
+      "total_examples": 604,
+      "time_seconds": 7331,
+      "scores": {
+        "tool_selection": 19.3,
+        "no_tool_accuracy": 94.6,
+        "anti_chatbot": 60.8,
+        "social_engineering_refusal": 85.0,
+        "voice_handling": 71.8,
+        "image_handling": 100.0,
+        "sticker_handling": 100.0
+      },
+      "by_category": {
+        "balance": {
+          "correct": 26,
+          "total": 56,
+          "accuracy": 46.4
+        },
+        "send": {
+          "correct": 4,
+          "total": 100,
+          "accuracy": 4.0
+        },
+        "price": {
+          "correct": 10,
+          "total": 56,
+          "accuracy": 17.9
+        },
+        "swap": {
+          "correct": 2,
+          "total": 50,
+          "accuracy": 4.0
+        },
+        "voice": {
+          "correct": 4,
+          "total": 15,
+          "accuracy": 26.7
+        },
+        "anti_chatbot": {
+          "correct": 10,
+          "total": 13,
+          "accuracy": 76.9
+        }
+      }
     }
   ]
 }