Update README.md

README.md

@@ -231,52 +231,63 @@ This model was evaluated on the well-known OpenLLM v1, OpenLLM v2 and HumanEval_
   <td><b>78.74</b></td>
   <td><b>99.87</b></td>
 </tr>
-
 <!-- OpenLLM V2 -->
 <tr>
-  <td rowspan="7"><b>OpenLLM V2</b></td>
+  <td rowspan="6"><b>OpenLLM V2</b></td>
   <td>BBH</td>
-  <td></td>
+  <td>63.67</td>
   <td>63.81</td>
-  <td></td>
+  <td>100.22</td>
 </tr>
 <tr>
   <td>MMLU-Pro</td>
-  <td></td>
+  <td>58.23</td>
   <td>57.99</td>
-  <td></td>
+  <td>99.59</td>
 </tr>
 <tr>
   <td>MuSR</td>
-  <td></td>
+  <td>43.25</td>
   <td>42.99</td>
-  <td></td>
+  <td>99.40</td>
 </tr>
 <tr>
   <td>IFEval</td>
-  <td></td>
   <td>88.25</td>
-  <td></td>
+  <td>88.25</td>
+  <td>100.00</td>
 </tr>
 <tr>
   <td>GPQA</td>
-  <td></td>
+  <td>29.28</td>
   <td>28.94</td>
-  <td></td>
+  <td>98.84</td>
+</tr>
+<tr>
+  <td><b>Average</b></td>
+  <td><b>56.54</b></td>
+  <td><b>56.40</b></td>
+  <td><b>99.75</b></td>
+</tr>
+<tr>
+  <td rowspan="3"><b>Reasoning</b></td>
+  <td>GPQA (Diamond, 0-shot)</td>
+  <td>72.22</td>
+  <td>69.19</td>
+  <td>95.80</td>
 </tr>
 <tr>
-  <td>Math Hard</td>
-  <td></td>
-  <td>56.80</td>
-  <td></td>
+  <td>Math-500 (0-shot)</td>
+  <td>95.00</td>
+  <td>94.20</td>
+  <td>99.16</td>
 </tr>
 <tr>
   <td><b>Average</b></td>
-  <td></td>
-  <td><b>56.46</b></td>
-  <td></td>
+  <td><b>83.61</b></td>
+  <td><b>81.70</b></td>
+  <td><b>97.72</b></td>
 </tr>
-
 <!-- Coding -->
 <tr>
   <td rowspan="1"><b>Coding</b></td>