Update README.md
Browse files
README.md
CHANGED
@@ -213,15 +213,15 @@ lm_eval \
|
|
213 |
<tr>
|
214 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
215 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
216 |
-
<td>34.
|
217 |
-
<td>35.
|
218 |
-
<td>103.
|
219 |
</tr>
|
220 |
<tr>
|
221 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
222 |
-
<td>
|
223 |
-
<td>
|
224 |
-
<td
|
225 |
</tr>
|
226 |
<tr>
|
227 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
@@ -231,27 +231,27 @@ lm_eval \
|
|
231 |
</tr>
|
232 |
<tr>
|
233 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
234 |
-
<td>
|
235 |
-
<td>
|
236 |
-
<td
|
237 |
</tr>
|
238 |
<tr>
|
239 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
240 |
-
<td>
|
241 |
-
<td>
|
242 |
-
<td
|
243 |
</tr>
|
244 |
<tr>
|
245 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
246 |
-
<td>
|
247 |
-
<td>
|
248 |
-
<td
|
249 |
</tr>
|
250 |
<tr>
|
251 |
<td><b>Average Score</b></td>
|
252 |
-
<td><b>
|
253 |
-
<td><b>
|
254 |
-
<td><b
|
255 |
</tr>
|
256 |
<tr>
|
257 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
213 |
<tr>
|
214 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
215 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
216 |
+
<td>34.63</td>
|
217 |
+
<td>35.70</td>
|
218 |
+
<td>103.1%</td>
|
219 |
</tr>
|
220 |
<tr>
|
221 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
222 |
+
<td>3.06</td>
|
223 |
+
<td>2.31</td>
|
224 |
+
<td>---</td>
|
225 |
</tr>
|
226 |
<tr>
|
227 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
|
|
231 |
</tr>
|
232 |
<tr>
|
233 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
234 |
+
<td>1.01</td>
|
235 |
+
<td>1.19</td>
|
236 |
+
<td>---</td>
|
237 |
</tr>
|
238 |
<tr>
|
239 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
240 |
+
<td>0.78</td>
|
241 |
+
<td>0.29</td>
|
242 |
+
<td>---</td>
|
243 |
</tr>
|
244 |
<tr>
|
245 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
246 |
+
<td>1.32</td>
|
247 |
+
<td>1.23</td>
|
248 |
+
<td>---</td>
|
249 |
</tr>
|
250 |
<tr>
|
251 |
<td><b>Average Score</b></td>
|
252 |
+
<td><b>6.80</b></td>
|
253 |
+
<td><b>6.79</b></td>
|
254 |
+
<td><b>---</b></td>
|
255 |
</tr>
|
256 |
<tr>
|
257 |
<td rowspan="4"><b>Coding</b></td>
|