Update README.md

README.md

@@ -173,9 +173,7 @@ The model was evaluated on the OpenLLMv1 leaderboard task, using [lm-evaluation-
 
 
 
-
 ### Accuracy
-
 <table>
   <thead>
     <tr>
@@ -191,97 +189,97 @@ The model was evaluated on the OpenLLMv1 leaderboard task, using [lm-evaluation-
     <tr>
       <td rowspan="7"><b>OpenLLM V1</b></td>
       <td>ARC-Challenge (Acc-Norm, 25-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>72.95</td>
+      <td>72.78</td>
+      <td>99.77</td>
     </tr>
     <tr>
       <td>GSM8K (Strict-Match, 5-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>74.15</td>
+      <td>74.53</td>
+      <td>100.51</td>
     </tr>
     <tr>
       <td>HellaSwag (Acc-Norm, 10-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>84.03</td>
+      <td>83.86</td>
+      <td>99.80</td>
     </tr>
     <tr>
       <td>MMLU (Acc, 5-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>81.99</td>
+      <td>81.97</td>
+      <td>99.97</td>
     </tr>
     <tr>
       <td>TruthfulQA (MC2, 0-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>59.18</td>
+      <td>58.72</td>
+      <td>99.22</td>
     </tr>
     <tr>
       <td>Winogrande (Acc, 5-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>76.01</td>
+      <td>75.22</td>
+      <td>98.96</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b>abc</b></td>
-      <td><b>ijk</b></td>
-      <td><b>xyz</b></td>
+      <td><b>74.72</b></td>
+      <td><b>74.51</b></td>
+      <td><b>99.72</b></td>
     </tr>
     <!-- OpenLLM Leaderboard V2 -->
     <tr>
       <td rowspan="7"><b>OpenLLM V2</b></td>
       <td>IFEval (Inst Level Strict Acc, 0-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>49.04</td>
+      <td>49.28</td>
+      <td>100.49</td>
     </tr>
     <tr>
       <td>BBH (Acc-Norm, 3-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>35.27</td>
+      <td>33.94</td>
+      <td>96.21</td>
     </tr>
     <tr>
       <td>Math-Hard (Exact-Match, 4-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>19.94</td>
+      <td>17.52</td>
+      <td>87.88</td>
     </tr>
     <tr>
       <td>GPQA (Acc-Norm, 0-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>26.01</td>
+      <td>24.41</td>
+      <td>93.87</td>
     </tr>
     <tr>
       <td>MUSR (Acc-Norm, 0-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>40.34</td>
+      <td>40.21</td>
+      <td>99.67</td>
     </tr>
     <tr>
       <td>MMLU-Pro (Acc, 5-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>12.38</td>
+      <td>12.35</td>
+      <td>99.73</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b>abc</b></td>
-      <td><b>ijk</b></td>
-      <td><b>xyz</b></td>
+      <td><b>30.50</b></td>
+      <td><b>29.62</b></td>
+      <td><b>97.11</b></td>
     </tr>
-    <!-- HumanEval -->
+    <!-- Coding -->
     <tr>
-      <td rowspan="2"><b>Coding</b></td>
+      <td rowspan="1"><b>Coding</b></td>
       <td>HumanEval Pass@1</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td><b>xyz</b></td>
+      <td>N/A</td>
+      <td>N/A</td>
+      <td>N/A</td>
     </tr>
   </tbody>
 </table>