Update README.md

README.md

@@ -179,113 +179,113 @@ lm_eval \
     <tr>
       <td rowspan="7"><b>OpenLLM V1</b></td>
       <td>ARC-Challenge (Acc-Norm, 25-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>63.65</td>
+      <td>63.57</td>
+      <td>99.9%</td>
     </tr>
     <tr>
       <td>GSM8K (Strict-Match, 5-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>93.03</td>
+      <td>93.56</td>
+      <td>100.6%</td>
     </tr>
     <tr>
       <td>HellaSwag (Acc-Norm, 10-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>84.85</td>
+      <td>85.15</td>
+      <td>100.4%</td>
     </tr>
     <tr>
       <td>MMLU (Acc, 5-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>78.04</td>
+      <td>78.01</td>
+      <td>100.0%</td>
     </tr>
     <tr>
       <td>TruthfulQA (MC2, 0-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>56.67</td>
+      <td>57.47</td>
+      <td>101.4%</td>
     </tr>
     <tr>
       <td>Winogrande (Acc, 5-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>78.22</td>
+      <td>78.37</td>
+      <td>100.2%</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b></b></td>
-      <td><b></b></td>
-      <td><b>%</b></td>
+      <td><b>75.74</b></td>
+      <td><b>76.02</b></td>
+      <td><b>100.4%</b></td>
     </tr>
     <tr>
       <td rowspan="7"><b>OpenLLM V2</b></td>
       <td>IFEval (Inst Level Strict Acc, 0-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>43.15</td>
+      <td>43.42</td>
+      <td>100.2%</td>
     </tr>
     <tr>
       <td>BBH (Acc-Norm, 3-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>64.32</td>
+      <td>62.78</td>
+      <td>97.6%</td>
     </tr>
     <tr>
       <td>Math-Hard (Exact-Match, 4-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>35.04</td>
+      <td>32.32</td>
+      <td>92.2%</td>
     </tr>
     <tr>
       <td>GPQA (Acc-Norm, 0-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>37.15</td>
+      <td>36.83</td>
+      <td>99.1%</td>
     </tr>
     <tr>
       <td>MUSR (Acc-Norm, 0-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>42.89</td>
+      <td>43.16</td>
+      <td>100.6%</td>
     </tr>
     <tr>
       <td>MMLU-Pro (Acc, 5-shot)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>47.22</td>
+      <td>47.30</td>
+      <td>100.2%</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
-      <td><b></b></td>
-      <td><b></b></td>
-      <td><b>%</b></td>
+      <td><b>44.96</b></td>
+      <td><b>44.30</b></td>
+      <td><b>98.5%</b></td>
     </tr>
     <tr>
       <td rowspan="4"><b>Coding</b></td>
       <td>HumanEval (pass@1)</td>
-      <td></td>
-      <td></td>
-      <td><b>%</b></td>
+      <td>81.10</td>
+      <td>81.00</td>
+      <td><b>99.9%</b></td>
     </tr>
     <tr>
       <td>HumanEval (pass@10)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>87.60</td>
+      <td>86.80</td>
+      <td>99.1%</td>
     </tr>
     <tr>
       <td>HumanEval+ (pass@10)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>75.20</td>
+      <td>75.80</td>
+      <td>100.8%</td>
     </tr>
     <tr>
       <td>HumanEval+ (pass@10)</td>
-      <td></td>
-      <td></td>
-      <td>%</td>
+      <td>83.10</td>
+      <td>83.40</td>
+      <td>100.4%</td>
     </tr>
   </tbody>
 </table>