Update README.md
Browse files
README.md
CHANGED
@@ -203,45 +203,45 @@ lm_eval \
|
|
203 |
<tr>
|
204 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
205 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
206 |
-
<td>
|
207 |
-
<td>42.
|
208 |
-
<td>99.
|
209 |
</tr>
|
210 |
<tr>
|
211 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
212 |
-
<td>
|
213 |
-
<td>
|
214 |
-
<td>
|
215 |
</tr>
|
216 |
<tr>
|
217 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
218 |
-
<td>
|
219 |
-
<td>
|
220 |
-
<td
|
221 |
</tr>
|
222 |
<tr>
|
223 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
224 |
-
<td>
|
225 |
-
<td>
|
226 |
-
<td
|
227 |
</tr>
|
228 |
<tr>
|
229 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
230 |
-
<td>
|
231 |
-
<td>
|
232 |
-
<td
|
233 |
</tr>
|
234 |
<tr>
|
235 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
236 |
-
<td>
|
237 |
-
<td>
|
238 |
-
<td
|
239 |
</tr>
|
240 |
<tr>
|
241 |
<td><b>Average Score</b></td>
|
242 |
-
<td><b>
|
243 |
-
<td><b>
|
244 |
-
<td><b>
|
245 |
</tr>
|
246 |
<tr>
|
247 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
203 |
<tr>
|
204 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
205 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
206 |
+
<td>42.45</td>
|
207 |
+
<td>42.11</td>
|
208 |
+
<td>99.2%</td>
|
209 |
</tr>
|
210 |
<tr>
|
211 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
212 |
+
<td>21.26</td>
|
213 |
+
<td>19.77</td>
|
214 |
+
<td>93.0%</td>
|
215 |
</tr>
|
216 |
<tr>
|
217 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
218 |
+
<td>0.00</td>
|
219 |
+
<td>0.00</td>
|
220 |
+
<td>---</td>
|
221 |
</tr>
|
222 |
<tr>
|
223 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
224 |
+
<td>9.51</td>
|
225 |
+
<td>6.97</td>
|
226 |
+
<td>---</td>
|
227 |
</tr>
|
228 |
<tr>
|
229 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
230 |
+
<td>14.87</td>
|
231 |
+
<td>14.60</td>
|
232 |
+
<td>---</td>
|
233 |
</tr>
|
234 |
<tr>
|
235 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
236 |
+
<td>4.27</td>
|
237 |
+
<td>5.76</td>
|
238 |
+
<td>---</td>
|
239 |
</tr>
|
240 |
<tr>
|
241 |
<td><b>Average Score</b></td>
|
242 |
+
<td><b>15.39</b></td>
|
243 |
+
<td><b>14.87</b></td>
|
244 |
+
<td><b>96.6%</b></td>
|
245 |
</tr>
|
246 |
<tr>
|
247 |
<td rowspan="4"><b>Coding</b></td>
|