Update README.md (#1)
Browse files- Update README.md (9425b670fcb016a6da5e14b64c86f69b7315e108)
Co-authored-by: Karna <[email protected]>
README.md
CHANGED
@@ -110,24 +110,24 @@ We report in the following table our internal pipeline benchmarks:
|
|
110 |
<tbody>
|
111 |
<tr>
|
112 |
<td>MMLU</td>
|
113 |
-
<td>67.
|
114 |
-
<td>65.
|
115 |
-
<td>66.
|
116 |
-
<td>67.
|
117 |
</tr>
|
118 |
<tr>
|
119 |
<td>MMLU-PRO</td>
|
120 |
-
<td>40.
|
121 |
-
<td>39.
|
122 |
-
<td>39.
|
123 |
-
<td>40.
|
124 |
</tr>
|
125 |
<tr>
|
126 |
<td>IFEval</td>
|
127 |
-
<td>75.
|
128 |
-
<td>72.
|
129 |
-
<td>74.
|
130 |
-
<td>
|
131 |
</tr>
|
132 |
</tbody>
|
133 |
</table>
|
|
|
110 |
<tbody>
|
111 |
<tr>
|
112 |
<td>MMLU</td>
|
113 |
+
<td>67.7</td>
|
114 |
+
<td>65.6</td>
|
115 |
+
<td>66.4</td>
|
116 |
+
<td>67.6</td>
|
117 |
</tr>
|
118 |
<tr>
|
119 |
<td>MMLU-PRO</td>
|
120 |
+
<td>40.9</td>
|
121 |
+
<td>39.1</td>
|
122 |
+
<td>39.9</td>
|
123 |
+
<td>40.9</td>
|
124 |
</tr>
|
125 |
<tr>
|
126 |
<td>IFEval</td>
|
127 |
+
<td>75.1</td>
|
128 |
+
<td>72.2</td>
|
129 |
+
<td>74.8</td>
|
130 |
+
<td>77.0</td>
|
131 |
</tr>
|
132 |
</tbody>
|
133 |
</table>
|