Update README.md

README.md

@@ -151,44 +151,44 @@ lm_eval \
       <td rowspan="7"><b>OpenLLM V1</b></td>
       <td>ARC Challenge</td>
       <td>68.43%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>68.86%</td>
+      <td>100.62%</td>
     </tr>
     <tr>
       <td>GSM8K</td>
       <td>88.10%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>88.02%</td>
+      <td>99.91%</td>
     </tr>
     <tr>
       <td>Hellaswag</td>
       <td>83.76%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>83.78%</td>
+      <td>100.02%</td>
     </tr>
     <tr>
       <td>MMLU</td>
       <td>72.15%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>71.80%</td>
+      <td>99.51%</td>
     </tr>
     <tr>
       <td>Truthfulqa (mc2)</td>
       <td>58.13%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>59.35%</td>
+      <td>102.09%</td>
     </tr>
     <tr>
       <td>Winogrande</td>
-      <td>79.40%%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>79.40%</td>
+      <td>79.48%</td>
+      <td>100.10%</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
       <td><b>74.99%</b></td>
-      <td><b>%</b></td>
-      <td><b>%</b></td>
+      <td><b>75.21%</b></td>
+      <td><b>100.29%</b></td>
     </tr>
     <tr>
       <td rowspan="3"><b>Vision Evals</b></td>