Add reasoning evals
Browse files
README.md
CHANGED
@@ -168,6 +168,31 @@ lm_eval \
|
|
168 |
</thead>
|
169 |
<tbody>
|
170 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
171 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
172 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
173 |
<td>58.79</td>
|
|
|
168 |
</thead>
|
169 |
<tbody>
|
170 |
<tr>
|
171 |
+
<td rowspan="4"><b>Reasoning</b></td>
|
172 |
+
<td>AIME 2024 (pass@1)</td>
|
173 |
+
<td>66.67</td>
|
174 |
+
<td>66.31</td>
|
175 |
+
<td>99.46%</td>
|
176 |
+
</tr>
|
177 |
+
<tr>
|
178 |
+
<td>MATH-500 (pass@1)</td>
|
179 |
+
<td>94.66</td>
|
180 |
+
<td>94.68</td>
|
181 |
+
<td>100.02%</td>
|
182 |
+
</tr>
|
183 |
+
<tr>
|
184 |
+
<td>GPQA Diamond (pass@1)</td>
|
185 |
+
<td>59.35</td>
|
186 |
+
<td>58.32</td>
|
187 |
+
<td>98.26%</td>
|
188 |
+
</tr>
|
189 |
+
<tr>
|
190 |
+
<td><b>Average Score</b></td>
|
191 |
+
<td><b>73.56</b></td>
|
192 |
+
<td><b>73.1</b></td>
|
193 |
+
<td><b>99.37%</b></td>
|
194 |
+
</tr>
|
195 |
+
<tr>
|
196 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
197 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
198 |
<td>58.79</td>
|