docs(readme): update

README.md

@@ -128,9 +128,9 @@ We report in the following table our internal pipeline benchmarks:
         <tr>
             <td rowspan="3">Math</td>
             <td>GSM8K (5-shot)</td>
-            <td>19.2</td>
-            <td>33.7</td>
-            <td><b>78.8</b></td>
+            <td>78.1</td>
+            <td>77.5</td>
+            <td><b>79.1</b></td>
         </tr>
         <tr>
             <td>GSM8k (8-shot, COT)</td>
@@ -145,7 +145,7 @@ We report in the following table our internal pipeline benchmarks:
             <td><b>33.1</b></td>
         </tr>
         <tr>
-            <td rowspan="6">Reasoning</td>
+            <td rowspan="5">Reasoning</td>
             <td>Arc Challenge (25-shot)</td>
             <td>46.6</td>
             <td>55.7</td>
@@ -175,12 +175,6 @@ We report in the following table our internal pipeline benchmarks:
             <td><b>53.9</b></td>
             <td>52.4</td>
         </tr>
-        <tr>
-            <td>BBH (3-shot, COT)</td>
-            <td>6.7</td>
-            <td>21.2</td>
-            <td><b>69.3</b></td>
-        </tr>
         <tr>
             <td rowspan="4">CommonSense Understanding</td>
             <td>PIQA (0-shot)</td>