Update README.md
Browse files
README.md
CHANGED
|
@@ -198,88 +198,88 @@ lm_eval \
|
|
| 198 |
<tr>
|
| 199 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 200 |
<td>arc_challenge</td>
|
| 201 |
-
<td>
|
| 202 |
-
<td>
|
| 203 |
-
<td>
|
| 204 |
</tr>
|
| 205 |
<tr>
|
| 206 |
<td>gsm8k</td>
|
| 207 |
-
<td>
|
| 208 |
-
<td>
|
| 209 |
-
<td>
|
| 210 |
</tr>
|
| 211 |
<tr>
|
| 212 |
<td>hellaswag</td>
|
| 213 |
-
<td>
|
| 214 |
-
<td>
|
| 215 |
-
<td>
|
| 216 |
</tr>
|
| 217 |
<tr>
|
| 218 |
<td>mmlu</td>
|
| 219 |
-
<td>
|
| 220 |
-
<td>
|
| 221 |
-
<td>
|
| 222 |
</tr>
|
| 223 |
<tr>
|
| 224 |
<td>truthfulqa_mc2</td>
|
| 225 |
-
<td>
|
| 226 |
-
<td>
|
| 227 |
-
<td>
|
| 228 |
</tr>
|
| 229 |
<tr>
|
| 230 |
<td>winogrande</td>
|
| 231 |
-
<td>
|
| 232 |
-
<td>
|
| 233 |
-
<td>97.
|
| 234 |
</tr>
|
| 235 |
<tr>
|
| 236 |
<td><b>Average</b></td>
|
| 237 |
-
<td>
|
| 238 |
-
<td>
|
| 239 |
-
<td><b>
|
| 240 |
</tr>
|
| 241 |
<tr>
|
| 242 |
<td rowspan="7"><b>Leaderboard</b></td>
|
| 243 |
<td>bbh</td>
|
| 244 |
-
<td>
|
| 245 |
-
<td>
|
| 246 |
-
<td>
|
| 247 |
</tr>
|
| 248 |
<tr>
|
| 249 |
<td>mmlu_pro</td>
|
| 250 |
-
<td>
|
| 251 |
-
<td>
|
| 252 |
-
<td>
|
| 253 |
</tr>
|
| 254 |
<tr>
|
| 255 |
<td>musr</td>
|
| 256 |
-
<td>
|
| 257 |
-
<td>
|
| 258 |
-
<td>
|
| 259 |
</tr>
|
| 260 |
<tr>
|
| 261 |
<td>ifeval</td>
|
| 262 |
-
<td>
|
| 263 |
-
<td>
|
| 264 |
-
<td>
|
| 265 |
</tr>
|
| 266 |
<tr>
|
| 267 |
<td>gpqa</td>
|
| 268 |
-
<td>30.
|
| 269 |
-
<td>
|
| 270 |
-
<td>
|
| 271 |
</tr>
|
| 272 |
<tr>
|
| 273 |
<td>math_hard</td>
|
| 274 |
-
<td>
|
| 275 |
-
<td>
|
| 276 |
-
<td>
|
| 277 |
</tr>
|
| 278 |
<tr>
|
| 279 |
<td><b>Average</b></td>
|
| 280 |
-
<td>
|
| 281 |
-
<td>
|
| 282 |
-
<td><b>
|
| 283 |
</tr>
|
| 284 |
</tbody>
|
| 285 |
</table>
|
|
|
|
| 198 |
<tr>
|
| 199 |
<td rowspan="7"><b>OpenLLM V1</b></td>
|
| 200 |
<td>arc_challenge</td>
|
| 201 |
+
<td>50.60</td>
|
| 202 |
+
<td>47.35</td>
|
| 203 |
+
<td>93.57%</td>
|
| 204 |
</tr>
|
| 205 |
<tr>
|
| 206 |
<td>gsm8k</td>
|
| 207 |
+
<td>48.07</td>
|
| 208 |
+
<td>24.34</td>
|
| 209 |
+
<td>50.65%</td>
|
| 210 |
</tr>
|
| 211 |
<tr>
|
| 212 |
<td>hellaswag</td>
|
| 213 |
+
<td>67.78</td>
|
| 214 |
+
<td>64.89</td>
|
| 215 |
+
<td>95.74%</td>
|
| 216 |
</tr>
|
| 217 |
<tr>
|
| 218 |
<td>mmlu</td>
|
| 219 |
+
<td>59.92</td>
|
| 220 |
+
<td>57.81</td>
|
| 221 |
+
<td>96.48%</td>
|
| 222 |
</tr>
|
| 223 |
<tr>
|
| 224 |
<td>truthfulqa_mc2</td>
|
| 225 |
+
<td>49.98</td>
|
| 226 |
+
<td>49.02</td>
|
| 227 |
+
<td>98.08%</td>
|
| 228 |
</tr>
|
| 229 |
<tr>
|
| 230 |
<td>winogrande</td>
|
| 231 |
+
<td>65.11</td>
|
| 232 |
+
<td>63.61</td>
|
| 233 |
+
<td>97.70%</td>
|
| 234 |
</tr>
|
| 235 |
<tr>
|
| 236 |
<td><b>Average</b></td>
|
| 237 |
+
<td>56.91</td>
|
| 238 |
+
<td>51.17</td>
|
| 239 |
+
<td><b>89.91%</b></td>
|
| 240 |
</tr>
|
| 241 |
<tr>
|
| 242 |
<td rowspan="7"><b>Leaderboard</b></td>
|
| 243 |
<td>bbh</td>
|
| 244 |
+
<td>53.32</td>
|
| 245 |
+
<td>51.35</td>
|
| 246 |
+
<td>96.30%</td>
|
| 247 |
</tr>
|
| 248 |
<tr>
|
| 249 |
<td>mmlu_pro</td>
|
| 250 |
+
<td>29.76</td>
|
| 251 |
+
<td>27.13</td>
|
| 252 |
+
<td>91.12%</td>
|
| 253 |
</tr>
|
| 254 |
<tr>
|
| 255 |
<td>musr</td>
|
| 256 |
+
<td>34.52</td>
|
| 257 |
+
<td>37.83</td>
|
| 258 |
+
<td>109.59%</td>
|
| 259 |
</tr>
|
| 260 |
<tr>
|
| 261 |
<td>ifeval</td>
|
| 262 |
+
<td>80.22</td>
|
| 263 |
+
<td>78.30</td>
|
| 264 |
+
<td>97.60%</td>
|
| 265 |
</tr>
|
| 266 |
<tr>
|
| 267 |
<td>gpqa</td>
|
| 268 |
+
<td>30.54</td>
|
| 269 |
+
<td>30.45</td>
|
| 270 |
+
<td>99.70%</td>
|
| 271 |
</tr>
|
| 272 |
<tr>
|
| 273 |
<td>math_hard</td>
|
| 274 |
+
<td>34.52</td>
|
| 275 |
+
<td>23.41</td>
|
| 276 |
+
<td>67.83%</td>
|
| 277 |
</tr>
|
| 278 |
<tr>
|
| 279 |
<td><b>Average</b></td>
|
| 280 |
+
<td>43.81</td>
|
| 281 |
+
<td>41.41</td>
|
| 282 |
+
<td><b>94.52%</b></td>
|
| 283 |
</tr>
|
| 284 |
</tbody>
|
| 285 |
</table>
|