Update README.md

Correct Math score and rounding

README.md

@@ -20,7 +20,7 @@ license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
 
 **Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
 
-This repository contains the **Falcon3-7B-Instruct**. It achieves state of art results (at release's time) on reasoning, language understanding, instruction following, code and mathematics tasks.
+This repository contains the **Falcon3-7B-Instruct**. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks.
 Falcon3-7B-Instruct supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K.
 
 ## Model Details
@@ -146,7 +146,7 @@ We report in the following table our internal pipeline benchmarks:
             <td>MATH Lvl-5 (4-shot)</td>
             <td>10.4</td>
             <td>26</td>
-            <td><b>33.1</b></td>
+            <td><b>29.4</b></td>
         </tr>
         <tr>
             <td rowspan="5">Reasoning</td>
@@ -207,15 +207,15 @@ We report in the following table our internal pipeline benchmarks:
         <tr>
             <td rowspan="2">Instructions following</td>
             <td>MT-Bench (avg)</td>
-            <td>7.86</td>
-            <td><b>8.54</b></td>
-            <td>8.36</td>
+            <td>7.9</td>
+            <td><b>8.5</b></td>
+            <td>8.4</td>
         </tr>
         <tr>
             <td>Alpaca (WC)</td>
-            <td>26.57</td>
+            <td>26.6</td>
             <td><b>31.5</b></td>
-            <td>26.13</td>
+            <td>26.1</td>
         </tr>
         <tr>
             <td>Tool use</td>