Update README.md

README.md

@@ -105,97 +105,90 @@ We report in the following table our internal pipeline benchmarks. For the bench
         <tr>
             <td rowspan="3">General</td>
             <td>MMLU (5-shot)</td>
-            <td>30.6%</td>
-            <td>68.7%</td>
-            <td>55.9%</td>
-            <td>65.3%</td>
+            <td>30.6</td>
+            <td>68.7</td>
+            <td>55.9</td>
+            <td>65.3</td>
         </tr>
         <tr>
             <td>MMLU-PRO (5-shot)*</td>
-            <td>32.4%</td>
-            <td>31.6%</td>
-            <td>21.8%</td>
-            <td>26.3%</td>
+            <td>32.4</td>
+            <td>31.6</td>
+            <td>21.8</td>
+            <td>26.3</td>
         </tr>
         <tr>
             <td>IFEval</td>
-            <td>69.9%</td>
-            <td>65.7%</td>
-            <td>78.8%</td>
-            <td>71.7%</td>
+            <td>69.9</td>
+            <td>65.7</td>
+            <td>78.8</td>
+            <td>71.7</td>
         </tr>
         <tr>
             <td rowspan="2">Math</td>
             <td>GSM8K (5-shot)</td>
-            <td>0%</td>
-            <td>74.9%</td>
-            <td>19.2%</td>
-            <td>65.2%</td>
+            <td>0</td>
+            <td>74.9</td>
+            <td>19.2</td>
+            <td>65.2</td>
         </tr>
         <tr>
             <td>MATH Lvl-5 (4-shot)</td>
-            <td>13.6%</td>
-            <td>6.9%</td>
-            <td>10.4%</td>
-            <td>27.3%</td>
+            <td>13.6</td>
+            <td>6.9</td>
+            <td>10.4</td>
+            <td>27.3</td>
         </tr>
         <tr>
             <td rowspan="4">Reasoning</td>
             <td>Arc Challenge (25-shot)</td>
-            <td>54%</td>
-            <td>54.3%</td>
-            <td>46.6%</td>
-            <td>53.7%</td>
+            <td>54</td>
+            <td>54.3</td>
+            <td>46.6</td>
+            <td>53.7</td>
         </tr>
         <tr>
             <td>GPQA (0-shot)*</td>
-            <td>10.3%</td>
-            <td>11.1%</td>
-            <td>33.6%</td>
-            <td>7.2%</td>
+            <td>10.3</td>
+            <td>11.1</td>
+            <td>6.2</td>
+            <td>7.2</td>
         </tr>
         <tr>
             <td>MUSR (0-shot)*</td>
-            <td>8.2%</td>
-            <td>12.2%</td>
-            <td>38.6%</td>
-            <td>8.3%</td>
+            <td>8.2</td>
+            <td>12.2</td>
+            <td>38.6</td>
+            <td>8.3</td>
         </tr>
         <tr>
             <td>BBH (3-shot)*</td>
-            <td>33.3%</td>
-            <td>35.3%</td>
-            <td>43.7%</td>
-            <td>25.2%</td>
+            <td>33.3</td>
+            <td>35.3</td>
+            <td>43.7</td>
+            <td>25.2</td>
         </tr>
         <tr>
             <td rowspan="4">CommonSense Understanding</td>
             <td>PIQA (0-shot)</td>
-            <td>75.6%</td>
-            <td>82.3%</td>
-            <td>78.9%</td>
-            <td>80.9%</td>
+            <td>75.6</td>
+            <td>82.3</td>
+            <td>78.9</td>
+            <td>80.9</td>
         </tr>
         <tr>
             <td>SciQ (0-shot)</td>
-            <td>29.2%</td>
-            <td>94.9%</td>
-            <td>80.2%</td>
-            <td>93.6%</td>
-        </tr>
-        <tr>
-            <td>Winogrande (0-shot)</td>
-            <td>75.9%</td>
-            <td>64.5%</td>
-            <td>-</td>
-            <td>-</td>
+            <td>29.2</td>
+            <td>94.9</td>
+            <td>80.2</td>
+            <td>93.6</td>
         </tr>
         <tr>
             <td>OpenbookQA (0-shot)</td>
-            <td>45.6%</td>
-            <td>34.6%</td>
-            <td>46.2%</td>
-            <td>47.2%</td>
+            <td>45.6</td>
+            <td>34.6</td>
+            <td>46.2</td>
+            <td>47.2</td>
         </tr>
     </tbody>
 </table>