Update README.md

README.md

@@ -90,14 +90,14 @@ We report in the following table our internal pipeline benchmarks:
             <td rowspan="3">General</td>
             <td>MMLU (5-shot)</td>
             <td>65.2</td>
-            <td>74.2</td>
+            <td><b>74.2</b></td>
             <td>70.8</td>
             <td>67.5</td>
         </tr>
         <tr>
             <td>MMLU-PRO (5-shot)</td>
             <td>32.7</td>
-            <td>43.5</td>
+            <td><b>43.5</b></td>
             <td>41.4</td>
             <td>39.2</td>
         </tr>
@@ -106,13 +106,13 @@ We report in the following table our internal pipeline benchmarks:
             <td>12.0</td>
             <td>33.9</td>
             <td>21.2</td>
-            <td>34.3</td>
+            <td><b>34.3</b></td>
         </tr>
         <tr>
             <td rowspan="2">Math</td>
             <td>GSM8K (5-shot)</td>
             <td>49.4</td>
-            <td>82.9</td>
+            <td><b>82.9</b></td>
             <td>69.1</td>
             <td>76.2</td>
         </tr>
@@ -121,14 +121,14 @@ We report in the following table our internal pipeline benchmarks:
             <td>4.1</td>
             <td>15.5</td>
             <td>10.5</td>
-            <td>18.0</td>
+            <td><b>18.0</b></td>
         </tr>
         <tr>
             <td rowspan="4">Reasoning</td>
             <td>Arc Challenge (25-shot)</td>
             <td>58.2</td>
             <td>63.2</td>
-            <td>67.5</td>
+            <td><b>67.5</b></td>
             <td>63.1</td>
         </tr>
         <tr>
@@ -136,20 +136,20 @@ We report in the following table our internal pipeline benchmarks:
             <td>31.0</td>
             <td>33.0</td>
             <td>33.4</td>
-            <td>35.5</td>
+            <td><b>35.5</b></td>
         </tr>
         <tr>
             <td>MUSR (0-shot)</td>
             <td>38.0</td>
             <td>44.2</td>
             <td>45.3</td>
-            <td>47.3</td>
+            <td><b>47.3</b></td>
         </tr>
         <tr>
             <td>BBH (3-shot)</td>
             <td>46.5</td>
             <td>54.0</td>
-            <td>54.3</td>
+            <td><b>54.3</b></td>
             <td>51.0</td>
         </tr>
         <tr>
@@ -157,28 +157,28 @@ We report in the following table our internal pipeline benchmarks:
             <td>PIQA (0-shot)</td>
             <td>81.2</td>
             <td>79.9</td>
-            <td>82.9</td>
+            <td><b>82.9</b></td>
             <td>79.1</td>
         </tr>
         <tr>
             <td>SciQ (0-shot)</td>
             <td>94.6</td>
             <td>95.2</td>
-            <td>97.1</td>
+            <td><b>97.1</b></td>
             <td>92.4</td>
         </tr>
         <tr>
             <td>Winogrande (0-shot)</td>
             <td>74.0</td>
             <td>72.9</td>
-            <td>74.2</td>
+            <td><b>74.2</b></td>
             <td>71.0</td>
         </tr>
         <tr>
             <td>OpenbookQA (0-shot)</td>
             <td>44.8</td>
             <td>47.0</td>
-            <td>47.2</td>
+            <td><b>47.2</b></td>
             <td>43.8</td>
         </tr>
     </tbody>