Add reasoning evals
Browse files
README.md
CHANGED
@@ -172,6 +172,31 @@ lm_eval \
|
|
172 |
</thead>
|
173 |
<tbody>
|
174 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
175 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
176 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
177 |
<td>63.65</td>
|
|
|
172 |
</thead>
|
173 |
<tbody>
|
174 |
<tr>
|
175 |
+
<td rowspan="4"><b>Reasoning</b></td>
|
176 |
+
<td>AIME 2024 (pass@1)</td>
|
177 |
+
<td>67.83</td>
|
178 |
+
<td>65.61</td>
|
179 |
+
<td>96.73%</td>
|
180 |
+
</tr>
|
181 |
+
<tr>
|
182 |
+
<td>MATH-500 (pass@1)</td>
|
183 |
+
<td>95.29</td>
|
184 |
+
<td>95.19</td>
|
185 |
+
<td>99.9%</td>
|
186 |
+
</tr>
|
187 |
+
<tr>
|
188 |
+
<td>GPQA Diamond (pass@1)</td>
|
189 |
+
<td>65.57</td>
|
190 |
+
<td>64.04</td>
|
191 |
+
<td>97.67%</td>
|
192 |
+
</tr>
|
193 |
+
<tr>
|
194 |
+
<td><b>Average Score</b></td>
|
195 |
+
<td><b>76.23</b></td>
|
196 |
+
<td><b>74.95</b></td>
|
197 |
+
<td><b>98.23%</b></td>
|
198 |
+
</tr>
|
199 |
+
<tr>
|
200 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
201 |
<td>ARC-Challenge (Acc-Norm, 25-shot)</td>
|
202 |
<td>63.65</td>
|