evalplus: update

Author: ganler

leaderboard.html

@@ -167,7 +167,7 @@ <h3>📝 Notes</h3>
               <a href="https://github.com/evalplus/humanevalplus_release"
                 >HumanEval+</a
               >
-              version 0.1.9;
+              version 0.1.10;
               <a href="https://github.com/evalplus/mbppplus_release">MBPP+</a>
               version 0.2.0.
             </li>

results.json

@@ -531,20 +531,20 @@
     "link": "https://huggingface.co/microsoft/wavecoder-ultra-6.7b",
     "open-data": "NONE",
     "pass@1": {
-      "humaneval": 73.8,
-      "humaneval+": 67.1,
-      "mbpp": 77.5,
-      "mbpp+": 65.1
+      "humaneval": 75.0,
+      "humaneval+": 69.5,
+      "mbpp": 74.9,
+      "mbpp+": 63.5
     },
-    "prompted": false,
+    "prompted": true,
     "size": 7.0
   },
   "Magicoder-S-CL-7B": {
     "link": "https://huggingface.co/ise-uiuc/Magicoder-S-CL-7B",
     "open-data": "Partial",
     "pass@1": {
       "humaneval": 70.7,
-      "humaneval+": 67.1,
+      "humaneval+": 67.7,
       "mbpp": 70.6,
       "mbpp+": 60.1
     },
@@ -1187,6 +1187,18 @@
     "prompted": true,
     "size": 7.0
   },
+  "Phi-3-mini-4k-instruct": {
+    "link": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct",
+    "open-data": "NONE",
+    "pass@1": {
+      "humaneval": 64.6,
+      "humaneval+": 59.1,
+      "mbpp": 65.9,
+      "mbpp+": 54.2
+    },
+    "prompted": true,
+    "size": 3.8
+  },
   "phi-2-2.7B": {
     "link": "https://huggingface.co/microsoft/phi-2",
     "open-data": "NONE",