Update README.md
Browse files
README.md
CHANGED
|
@@ -172,88 +172,88 @@ lm_eval \
|
|
| 172 |
<tr>
|
| 173 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 174 |
<td>arc_challenge</td>
|
| 175 |
-
<td>60
|
| 176 |
-
<td>
|
| 177 |
-
<td>
|
| 178 |
</tr>
|
| 179 |
<tr>
|
| 180 |
<td>gsm8k</td>
|
| 181 |
-
<td>
|
| 182 |
-
<td>
|
| 183 |
-
<td>
|
| 184 |
</tr>
|
| 185 |
<tr>
|
| 186 |
<td>hellaswag</td>
|
| 187 |
-
<td>
|
| 188 |
-
<td>
|
| 189 |
-
<td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
| 192 |
<td>mmlu</td>
|
| 193 |
-
<td>
|
| 194 |
-
<td>
|
| 195 |
-
<td>
|
| 196 |
</tr>
|
| 197 |
<tr>
|
| 198 |
<td>truthfulqa_mc2</td>
|
| 199 |
-
<td>
|
| 200 |
-
<td>
|
| 201 |
-
<td>99.
|
| 202 |
</tr>
|
| 203 |
<tr>
|
| 204 |
<td>winogrande</td>
|
| 205 |
-
<td>
|
| 206 |
-
<td>
|
| 207 |
-
<td>
|
| 208 |
</tr>
|
| 209 |
<tr>
|
| 210 |
<td><b>Average</b></td>
|
| 211 |
-
<td>
|
| 212 |
-
<td>
|
| 213 |
-
<td><b>
|
| 214 |
</tr>
|
| 215 |
<tr>
|
| 216 |
<td rowspan="7"><b>Leaderboard</b></td>
|
| 217 |
<td>bbh</td>
|
| 218 |
-
<td>
|
| 219 |
-
<td>
|
| 220 |
-
<td>99.
|
| 221 |
</tr>
|
| 222 |
<tr>
|
| 223 |
<td>mmlu_pro</td>
|
| 224 |
-
<td>
|
| 225 |
-
<td>
|
| 226 |
-
<td>
|
| 227 |
</tr>
|
| 228 |
<tr>
|
| 229 |
<td>musr</td>
|
| 230 |
-
<td>
|
| 231 |
-
<td>
|
| 232 |
-
<td>103.
|
| 233 |
</tr>
|
| 234 |
<tr>
|
| 235 |
<td>ifeval</td>
|
| 236 |
-
<td>
|
| 237 |
-
<td>
|
| 238 |
-
<td>
|
| 239 |
</tr>
|
| 240 |
<tr>
|
| 241 |
<td>gpqa</td>
|
| 242 |
-
<td>30.
|
| 243 |
-
<td>
|
| 244 |
-
<td>
|
| 245 |
</tr>
|
| 246 |
<tr>
|
| 247 |
<td>math_hard</td>
|
| 248 |
-
<td>
|
| 249 |
-
<td>
|
| 250 |
-
<td>
|
| 251 |
</tr>
|
| 252 |
<tr>
|
| 253 |
<td><b>Average</b></td>
|
| 254 |
-
<td>
|
| 255 |
-
<td>
|
| 256 |
-
<td><b>100.
|
| 257 |
</tr>
|
| 258 |
</tbody>
|
| 259 |
-
</table>
|
|
|
|
| 172 |
<tr>
|
| 173 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 174 |
<td>arc_challenge</td>
|
| 175 |
+
<td>50.60</td>
|
| 176 |
+
<td>50.09</td>
|
| 177 |
+
<td>99.00%</td>
|
| 178 |
</tr>
|
| 179 |
<tr>
|
| 180 |
<td>gsm8k</td>
|
| 181 |
+
<td>48.07</td>
|
| 182 |
+
<td>54.51</td>
|
| 183 |
+
<td>113.40%</td>
|
| 184 |
</tr>
|
| 185 |
<tr>
|
| 186 |
<td>hellaswag</td>
|
| 187 |
+
<td>67.78</td>
|
| 188 |
+
<td>65.67</td>
|
| 189 |
+
<td>96.89%</td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
| 192 |
<td>mmlu</td>
|
| 193 |
+
<td>59.92</td>
|
| 194 |
+
<td>60.16</td>
|
| 195 |
+
<td>100.40%</td>
|
| 196 |
</tr>
|
| 197 |
<tr>
|
| 198 |
<td>truthfulqa_mc2</td>
|
| 199 |
+
<td>49.98</td>
|
| 200 |
+
<td>49.48</td>
|
| 201 |
+
<td>99.00%</td>
|
| 202 |
</tr>
|
| 203 |
<tr>
|
| 204 |
<td>winogrande</td>
|
| 205 |
+
<td>65.11</td>
|
| 206 |
+
<td>63.85</td>
|
| 207 |
+
<td>98.06%</td>
|
| 208 |
</tr>
|
| 209 |
<tr>
|
| 210 |
<td><b>Average</b></td>
|
| 211 |
+
<td>56.91</td>
|
| 212 |
+
<td>57.29</td>
|
| 213 |
+
<td><b>100.67%</b></td>
|
| 214 |
</tr>
|
| 215 |
<tr>
|
| 216 |
<td rowspan="7"><b>Leaderboard</b></td>
|
| 217 |
<td>bbh</td>
|
| 218 |
+
<td>53.32</td>
|
| 219 |
+
<td>52.99</td>
|
| 220 |
+
<td>99.38%</td>
|
| 221 |
</tr>
|
| 222 |
<tr>
|
| 223 |
<td>mmlu_pro</td>
|
| 224 |
+
<td>29.76</td>
|
| 225 |
+
<td>29.36</td>
|
| 226 |
+
<td>98.66%</td>
|
| 227 |
</tr>
|
| 228 |
<tr>
|
| 229 |
<td>musr</td>
|
| 230 |
+
<td>34.52</td>
|
| 231 |
+
<td>35.85</td>
|
| 232 |
+
<td>103.85%</td>
|
| 233 |
</tr>
|
| 234 |
<tr>
|
| 235 |
<td>ifeval</td>
|
| 236 |
+
<td>80.22</td>
|
| 237 |
+
<td>80.58</td>
|
| 238 |
+
<td>100.45%</td>
|
| 239 |
</tr>
|
| 240 |
<tr>
|
| 241 |
<td>gpqa</td>
|
| 242 |
+
<td>30.54</td>
|
| 243 |
+
<td>29.36</td>
|
| 244 |
+
<td>96.14%</td>
|
| 245 |
</tr>
|
| 246 |
<tr>
|
| 247 |
<td>math_hard</td>
|
| 248 |
+
<td>34.52</td>
|
| 249 |
+
<td>34.97</td>
|
| 250 |
+
<td>101.30%</td>
|
| 251 |
</tr>
|
| 252 |
<tr>
|
| 253 |
<td><b>Average</b></td>
|
| 254 |
+
<td>43.81</td>
|
| 255 |
+
<td>43.85</td>
|
| 256 |
+
<td><b>100.09%</b></td>
|
| 257 |
</tr>
|
| 258 |
</tbody>
|
| 259 |
+
</table>
|