Update README.md
Browse files
README.md
CHANGED
|
@@ -194,15 +194,15 @@ lm_eval \
|
|
| 194 |
<tr>
|
| 195 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
| 196 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
| 197 |
-
<td>39.
|
| 198 |
-
<td>39.
|
| 199 |
-
<td>
|
| 200 |
</tr>
|
| 201 |
<tr>
|
| 202 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
| 203 |
-
<td>
|
| 204 |
-
<td>
|
| 205 |
-
<td
|
| 206 |
</tr>
|
| 207 |
<tr>
|
| 208 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
|
@@ -212,27 +212,27 @@ lm_eval \
|
|
| 212 |
</tr>
|
| 213 |
<tr>
|
| 214 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
| 215 |
-
<td>
|
| 216 |
-
<td>
|
| 217 |
-
<td
|
| 218 |
</tr>
|
| 219 |
<tr>
|
| 220 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
| 221 |
-
<td>
|
| 222 |
-
<td>
|
| 223 |
-
<td
|
| 224 |
</tr>
|
| 225 |
<tr>
|
| 226 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
| 227 |
-
<td>
|
| 228 |
-
<td>
|
| 229 |
-
<td
|
| 230 |
</tr>
|
| 231 |
<tr>
|
| 232 |
<td><b>Average Score</b></td>
|
| 233 |
-
<td><b>
|
| 234 |
-
<td><b>
|
| 235 |
-
<td><b
|
| 236 |
</tr>
|
| 237 |
<tr>
|
| 238 |
<td rowspan="4"><b>Coding</b></td>
|
|
|
|
| 194 |
<tr>
|
| 195 |
<td rowspan="7"><b>OpenLLM V2</b></td>
|
| 196 |
<td>IFEval (Inst Level Strict Acc, 0-shot)</td>
|
| 197 |
+
<td>39.38</td>
|
| 198 |
+
<td>39.01</td>
|
| 199 |
+
<td>99.1%</td>
|
| 200 |
</tr>
|
| 201 |
<tr>
|
| 202 |
<td>BBH (Acc-Norm, 3-shot)</td>
|
| 203 |
+
<td>6.97</td>
|
| 204 |
+
<td>6.19</td>
|
| 205 |
+
<td>---</td>
|
| 206 |
</tr>
|
| 207 |
<tr>
|
| 208 |
<td>Math-Hard (Exact-Match, 4-shot)</td>
|
|
|
|
| 212 |
</tr>
|
| 213 |
<tr>
|
| 214 |
<td>GPQA (Acc-Norm, 0-shot)</td>
|
| 215 |
+
<td>1.81</td>
|
| 216 |
+
<td>1.63</td>
|
| 217 |
+
<td>---</td>
|
| 218 |
</tr>
|
| 219 |
<tr>
|
| 220 |
<td>MUSR (Acc-Norm, 0-shot)</td>
|
| 221 |
+
<td>4.68</td>
|
| 222 |
+
<td>5.08</td>
|
| 223 |
+
<td>---</td>
|
| 224 |
</tr>
|
| 225 |
<tr>
|
| 226 |
<td>MMLU-Pro (Acc, 5-shot)</td>
|
| 227 |
+
<td>1.66</td>
|
| 228 |
+
<td>1.76</td>
|
| 229 |
+
<td>---</td>
|
| 230 |
</tr>
|
| 231 |
<tr>
|
| 232 |
<td><b>Average Score</b></td>
|
| 233 |
+
<td><b>9.08</b></td>
|
| 234 |
+
<td><b>8.94</b></td>
|
| 235 |
+
<td><b>---</b></td>
|
| 236 |
</tr>
|
| 237 |
<tr>
|
| 238 |
<td rowspan="4"><b>Coding</b></td>
|