Update README.md
Browse files
README.md
CHANGED
|
@@ -221,45 +221,45 @@ lm_eval \
|
|
| 221 |
<tr>
|
| 222 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
| 223 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
| 224 |
-
<td>
|
| 225 |
-
<td>
|
| 226 |
-
<td>100.
|
| 227 |
</tr>
|
| 228 |
<tr>
|
| 229 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
| 230 |
-
<td>
|
| 231 |
-
<td>
|
| 232 |
-
<td>97.
|
| 233 |
</tr>
|
| 234 |
<tr>
|
| 235 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
| 236 |
-
<td>
|
| 237 |
-
<td>
|
| 238 |
-
<td
|
| 239 |
</tr>
|
| 240 |
<tr>
|
| 241 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
| 242 |
-
<td>
|
| 243 |
-
<td>
|
| 244 |
-
<td
|
| 245 |
</tr>
|
| 246 |
<tr>
|
| 247 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
| 248 |
-
<td>
|
| 249 |
-
<td>
|
| 250 |
-
<td
|
| 251 |
</tr>
|
| 252 |
<tr>
|
| 253 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
| 254 |
-
<td>
|
| 255 |
-
<td>
|
| 256 |
-
<td
|
| 257 |
</tr>
|
| 258 |
<tr>
|
| 259 |
<td><b>Average Score</b></td>
|
| 260 |
-
<td><b>
|
| 261 |
-
<td><b>
|
| 262 |
-
<td><b>
|
| 263 |
</tr>
|
| 264 |
<tr>
|
| 265 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
|
| 221 |
<tr>
|
| 222 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
| 223 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
| 224 |
+
<td>42.45</td>
|
| 225 |
+
<td>42.51</td>
|
| 226 |
+
<td>100.1%</td>
|
| 227 |
</tr>
|
| 228 |
<tr>
|
| 229 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
| 230 |
+
<td>21.26</td>
|
| 231 |
+
<td>20.78</td>
|
| 232 |
+
<td>97.8%</td>
|
| 233 |
</tr>
|
| 234 |
<tr>
|
| 235 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
| 236 |
+
<td>0.00</td>
|
| 237 |
+
<td>0.00</td>
|
| 238 |
+
<td>---</td>
|
| 239 |
</tr>
|
| 240 |
<tr>
|
| 241 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
| 242 |
+
<td>9.51</td>
|
| 243 |
+
<td>7.25</td>
|
| 244 |
+
<td>---</td>
|
| 245 |
</tr>
|
| 246 |
<tr>
|
| 247 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
| 248 |
+
<td>14.87</td>
|
| 249 |
+
<td>15.24</td>
|
| 250 |
+
<td>---</td>
|
| 251 |
</tr>
|
| 252 |
<tr>
|
| 253 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
| 254 |
+
<td>4.27</td>
|
| 255 |
+
<td>5.62</td>
|
| 256 |
+
<td>---</td>
|
| 257 |
</tr>
|
| 258 |
<tr>
|
| 259 |
<td><b>Average Score</b></td>
|
| 260 |
+
<td><b>15.39</b></td>
|
| 261 |
+
<td><b>15.23</b></td>
|
| 262 |
+
<td><b>99.0%</b></td>
|
| 263 |
</tr>
|
| 264 |
<tr>
|
| 265 |
<td rowspan="4"><b>Coding</b></td>
|