Add reasoning evals
Browse files
README.md
CHANGED
|
@@ -176,6 +176,31 @@ lm_eval \
|
|
| 176 |
</thead>
|
| 177 |
<tbody>
|
| 178 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 180 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
| 181 |
<td>63.65</td>
|
|
|
|
| 176 |
</thead>
|
| 177 |
<tbody>
|
| 178 |
<tr>
|
| 179 |
+
<td rowspan="4"><b>Reasoning</b></td>
|
| 180 |
+
<td>AIME 2024 (pass@1)</td>
|
| 181 |
+
<td>67.83</td>
|
| 182 |
+
<td>67.78</td>
|
| 183 |
+
<td>99.93%</td>
|
| 184 |
+
</tr>
|
| 185 |
+
<tr>
|
| 186 |
+
<td>MATH-500 (pass@1)</td>
|
| 187 |
+
<td>95.29</td>
|
| 188 |
+
<td>95.27</td>
|
| 189 |
+
<td>99.98%</td>
|
| 190 |
+
</tr>
|
| 191 |
+
<tr>
|
| 192 |
+
<td>GPQA Diamond (pass@1)</td>
|
| 193 |
+
<td>65.57</td>
|
| 194 |
+
<td>65.01</td>
|
| 195 |
+
<td>99.15%</td>
|
| 196 |
+
</tr>
|
| 197 |
+
<tr>
|
| 198 |
+
<td><b>Average Score</b></td>
|
| 199 |
+
<td><b>76.23</b></td>
|
| 200 |
+
<td><b>76.02</b></td>
|
| 201 |
+
<td><b>99.72%</b></td>
|
| 202 |
+
</tr>
|
| 203 |
+
<tr>
|
| 204 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 205 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
| 206 |
<td>63.65</td>
|