Update README.md
Browse files
README.md
CHANGED
@@ -209,15 +209,15 @@ lm_eval \
|
|
209 |
<tr>
|
210 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
211 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
212 |
-
<td>39.
|
213 |
-
<td
|
214 |
-
<td
|
215 |
</tr>
|
216 |
<tr>
|
217 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
218 |
-
<td>
|
219 |
-
<td
|
220 |
-
<td
|
221 |
</tr>
|
222 |
<tr>
|
223 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
@@ -227,27 +227,27 @@ lm_eval \
|
|
227 |
</tr>
|
228 |
<tr>
|
229 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
230 |
-
<td>
|
231 |
-
<td
|
232 |
-
<td
|
233 |
</tr>
|
234 |
<tr>
|
235 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
236 |
-
<td>
|
237 |
-
<td
|
238 |
-
<td
|
239 |
</tr>
|
240 |
<tr>
|
241 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
242 |
-
<td>
|
243 |
-
<td
|
244 |
-
<td
|
245 |
</tr>
|
246 |
<tr>
|
247 |
<td><b>Average Score</b></td>
|
248 |
-
<td><b>
|
249 |
-
<td><b
|
250 |
-
<td><b
|
251 |
</tr>
|
252 |
<tr>
|
253 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
209 |
<tr>
|
210 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
211 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
212 |
+
<td>39.38</td>
|
213 |
+
<td>39.38</td>
|
214 |
+
<td>100.0%</td>
|
215 |
</tr>
|
216 |
<tr>
|
217 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
218 |
+
<td>6.97</td>
|
219 |
+
<td>7.48</td>
|
220 |
+
<td>---</td>
|
221 |
</tr>
|
222 |
<tr>
|
223 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
|
|
227 |
</tr>
|
228 |
<tr>
|
229 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
230 |
+
<td>1.81</td>
|
231 |
+
<td>0.99</td>
|
232 |
+
<td>---</td>
|
233 |
</tr>
|
234 |
<tr>
|
235 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
236 |
+
<td>4.68</td>
|
237 |
+
<td>3.80</td>
|
238 |
+
<td>---</td>
|
239 |
</tr>
|
240 |
<tr>
|
241 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
242 |
+
<td>1.66</td>
|
243 |
+
<td>1.74</td>
|
244 |
+
<td>---</td>
|
245 |
</tr>
|
246 |
<tr>
|
247 |
<td><b>Average Score</b></td>
|
248 |
+
<td><b>9.08</b></td>
|
249 |
+
<td><b>8.90</b></td>
|
250 |
+
<td><b>---</b></td>
|
251 |
</tr>
|
252 |
<tr>
|
253 |
<td rowspan="4"><b>Coding</b></td>
|