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>61.01</td>
-      <td>60.58</td>
-      <td>xyz</td>
+      <td>60.92</td>
+      <td>60.92</td>
+      <td>100.00</td>
     </tr>
     <tr>
       <td>GSM8K (Strict-Match, 5-shot)</td>
-      <td>70.51</td>
-      <td>70.96</td>
-      <td>xyz</td>
+      <td>71.11</td>
+      <td>70.66</td>
+      <td>99.36</td>
     </tr>
     <tr>
       <td>HellaSwag (Acc-Norm, 10-shot)</td>
-      <td>80.74</td>
-      <td>80.35</td>
-      <td>xyz</td>
+      <td>80.75</td>
+      <td>80.48</td>
+      <td>99.67</td>
     </tr>
     <tr>
       <td>MMLU (Acc, 5-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>68.20</td>
+      <td>67.96</td>
+      <td>99.64</td>
     </tr>
     <tr>
       <td>TruthfulQA (MC2, 0-shot)</td>
-      <td>54.55</td>
-      <td>54.02</td>
-      <td>xyz</td>
+      <td>54.54</td>
+      <td>54.18</td>
+      <td>99.34</td>
     </tr>
     <tr>
       <td>Winogrande (Acc, 5-shot)</td>
-      <td>78.37</td>
-      <td>77.51</td>
-      <td>xyz</td>
+      <td>78.45</td>
+      <td>78.14</td>
+      <td>99.60</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>69.00</b></td>
+      <td><b>68.72</b></td>
+      <td><b>99.59</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>60.19</td>
-      <td>xyz</td>
+      <td>81.89</td>
+      <td>81.41</td>
+      <td>99.41</td>
     </tr>
     <tr>
       <td>BBH (Acc-Norm, 3-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>50.70</td>
+      <td>50.96</td>
+      <td>100.51</td>
     </tr>
     <tr>
       <td>Math-Hard (Exact-Match, 4-shot)</td>
-      <td>abc</td>
-      <td>ijk</td>
-      <td>xyz</td>
+      <td>20.24</td>
+      <td>20.77</td>
+      <td>102.61</td>
     </tr>
     <tr>
       <td>GPQA (Acc-Norm, 0-shot)</td>
-      <td>abc</td>
-      <td>32.55</td>
-      <td>xyz</td>
+      <td>29.53</td>
+      <td>29.95</td>
+      <td>101.42</td>
     </tr>
     <tr>
       <td>MUSR (Acc-Norm, 0-shot)</td>
-      <td>abc</td>
-      <td>39.81</td>
-      <td>xyz</td>
+      <td>38.89</td>
+      <td>38.62</td>
+      <td>99.32</td>
     </tr>
     <tr>
       <td>MMLU-Pro (Acc, 5-shot)</td>
-      <td>abc</td>
-      <td>37.50</td>
-      <td>xyz</td>
+      <td>37.71</td>
+      <td>37.48</td>
+      <td>99.38</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>43.16</b></td>
+      <td><b>43.20</b></td>
+      <td><b>100.09</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>