Add reasoning evals
Browse files
README.md
CHANGED
|
@@ -149,6 +149,31 @@ lm_eval \
|
|
| 149 |
</thead>
|
| 150 |
<tbody>
|
| 151 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 153 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
| 154 |
<td>58.79</td>
|
|
|
|
| 149 |
</thead>
|
| 150 |
<tbody>
|
| 151 |
<tr>
|
| 152 |
+
<td rowspan="4"><b>Reasoning</b></td>
|
| 153 |
+
<td>AIME 2024 (pass@1)</td>
|
| 154 |
+
<td>66.67</td>
|
| 155 |
+
<td>68.13</td>
|
| 156 |
+
<td>102.19%</td>
|
| 157 |
+
</tr>
|
| 158 |
+
<tr>
|
| 159 |
+
<td>MATH-500 (pass@1)</td>
|
| 160 |
+
<td>94.66</td>
|
| 161 |
+
<td>94.63</td>
|
| 162 |
+
<td>99.97%</td>
|
| 163 |
+
</tr>
|
| 164 |
+
<tr>
|
| 165 |
+
<td>GPQA Diamond (pass@1)</td>
|
| 166 |
+
<td>59.35</td>
|
| 167 |
+
<td>60.1</td>
|
| 168 |
+
<td>101.26%</td>
|
| 169 |
+
</tr>
|
| 170 |
+
<tr>
|
| 171 |
+
<td><b>Average Score</b></td>
|
| 172 |
+
<td><b>73.56</b></td>
|
| 173 |
+
<td><b>74.29</b></td>
|
| 174 |
+
<td><b>100.99%</b></td>
|
| 175 |
+
</tr>
|
| 176 |
+
<tr>
|
| 177 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 178 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
| 179 |
<td>58.79</td>
|