Add reasoning evals
Browse files
README.md
CHANGED
|
@@ -147,6 +147,31 @@ lm_eval \
|
|
| 147 |
</tr>
|
| 148 |
</thead>
|
| 149 |
<tbody>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
<tr>
|
| 151 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 152 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
|
|
|
| 147 |
</tr>
|
| 148 |
</thead>
|
| 149 |
<tbody>
|
| 150 |
+
<tr>
|
| 151 |
+
<td rowspan="4"><b>Reasoning</b></td>
|
| 152 |
+
<td>AIME 2024 (pass@1)</td>
|
| 153 |
+
<td>49.25</td>
|
| 154 |
+
<td>50.83</td>
|
| 155 |
+
<td>103.21%</td>
|
| 156 |
+
</tr>
|
| 157 |
+
<tr>
|
| 158 |
+
<td>MATH-500 (pass@1)</td>
|
| 159 |
+
<td>90.18</td>
|
| 160 |
+
<td>90.24</td>
|
| 161 |
+
<td>100.07%</td>
|
| 162 |
+
</tr>
|
| 163 |
+
<tr>
|
| 164 |
+
<td>GPQA Diamond (pass@1)</td>
|
| 165 |
+
<td>49.27</td>
|
| 166 |
+
<td>48.71</td>
|
| 167 |
+
<td>98.86%</td>
|
| 168 |
+
</tr>
|
| 169 |
+
<tr>
|
| 170 |
+
<td><b>Average Score</b></td>
|
| 171 |
+
<td><b>62.9</b></td>
|
| 172 |
+
<td><b>63.26</b></td>
|
| 173 |
+
<td><b>100.57%</b></td>
|
| 174 |
+
</tr>
|
| 175 |
<tr>
|
| 176 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 177 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|