Update README.md

README.md

@@ -159,6 +159,7 @@ evalplus.evaluate \
 
 ### Accuracy
 
+
 <table>
   <thead>
     <tr>
@@ -173,52 +174,52 @@ evalplus.evaluate \
     <tr>
       <td rowspan="7"><b>OpenLLM Leaderboard V1</b></td>
       <td>ARC-Challenge (Acc-Norm, 25-shot)</td>
-      <td>55.63</td>
+      <td>53.75</td>
       <td>53.50</td>
-      <td>96.17</td>
+      <td>99.54</td>
     </tr>
     <tr>
       <td>GSM8K (Strict-Match, 5-shot)</td>
-      <td>60.96</td>
+      <td>47.84</td>
       <td>46.10</td>
-      <td>75.63</td>
-    </tr>
+      <td>96.36</td>
+    </tr>    
     <tr>
       <td>HellaSwag (Acc-Norm, 10-shot)</td>
-      <td>75.21</td>
+      <td>77.94</td>
       <td>77.76</td>
-      <td>103.39</td>
+      <td>99.77</td>
     </tr>
     <tr>
       <td>MMLU (Acc, 5-shot)</td>
-      <td>54.38</td>
+      <td>52.88</td>
       <td>52.61</td>
-      <td>96.75</td>
+      <td>99.49</td>
     </tr>
     <tr>
       <td>TruthfulQA (MC2, 0-shot)</td>
-      <td>55.93</td>
+      <td>39.04</td>
       <td>39.84</td>
-      <td>71.23</td>
+      <td>102.05</td>
     </tr>
     <tr>
       <td>Winogrande (Acc, 5-shot)</td>
-      <td>69.67</td>
       <td>74.43</td>
-      <td>106.84</td>
+      <td>74.43</td>
+      <td>100.00</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b>61.98</b></td>
+      <td><b>57.65</b></td>
       <td><b>57.37</b></td>
-      <td><b>92.57</b></td>
+      <td><b>99.52</b></td>
     </tr>
     <tr>
       <td rowspan="2"><b>HumanEval</b></td>
       <td>HumanEval Pass@1</td>
       <td>30.00</td>
       <td>30.40</td>
-      <td><b>101.33</b></td>
+      <td>101.33</td>
     </tr>
   </tbody>
 </table>
@@ -226,3 +227,4 @@ evalplus.evaluate \
 
 
 
+