Update README.md
Browse files
README.md
CHANGED
@@ -193,15 +193,15 @@ lm_eval \
|
|
193 |
<tr>
|
194 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
195 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
196 |
-
<td>38.
|
197 |
-
<td>38.
|
198 |
-
<td>
|
199 |
</tr>
|
200 |
<tr>
|
201 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
202 |
-
<td>
|
203 |
-
<td>
|
204 |
-
<td
|
205 |
</tr>
|
206 |
<tr>
|
207 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
@@ -211,27 +211,27 @@ lm_eval \
|
|
211 |
</tr>
|
212 |
<tr>
|
213 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
214 |
-
<td>
|
215 |
-
<td>
|
216 |
-
<td
|
217 |
</tr>
|
218 |
<tr>
|
219 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
220 |
-
<td>
|
221 |
-
<td>
|
222 |
-
<td
|
223 |
</tr>
|
224 |
<tr>
|
225 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
226 |
-
<td>
|
227 |
-
<td>
|
228 |
-
<td
|
229 |
</tr>
|
230 |
<tr>
|
231 |
<td><b>Average Score</b></td>
|
232 |
-
<td><b>
|
233 |
-
<td><b>
|
234 |
-
<td><b
|
235 |
</tr>
|
236 |
<tr>
|
237 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
193 |
<tr>
|
194 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
195 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
196 |
+
<td>38.37</td>
|
197 |
+
<td>38.67</td>
|
198 |
+
<td>100.8%</td>
|
199 |
</tr>
|
200 |
<tr>
|
201 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
202 |
+
<td>7.43</td>
|
203 |
+
<td>7.48</td>
|
204 |
+
<td>---</td>
|
205 |
</tr>
|
206 |
<tr>
|
207 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
|
|
211 |
</tr>
|
212 |
<tr>
|
213 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
214 |
+
<td>1.51</td>
|
215 |
+
<td>0.94</td>
|
216 |
+
<td>---</td>
|
217 |
</tr>
|
218 |
<tr>
|
219 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
220 |
+
<td>1.86</td>
|
221 |
+
<td>1.27</td>
|
222 |
+
<td>---</td>
|
223 |
</tr>
|
224 |
<tr>
|
225 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
226 |
+
<td>1.61</td>
|
227 |
+
<td>1.60</td>
|
228 |
+
<td>---</td>
|
229 |
</tr>
|
230 |
<tr>
|
231 |
<td><b>Average Score</b></td>
|
232 |
+
<td><b>8.47</b></td>
|
233 |
+
<td><b>8.33</b></td>
|
234 |
+
<td><b>---</b></td>
|
235 |
</tr>
|
236 |
<tr>
|
237 |
<td rowspan="4"><b>Coding</b></td>
|