Update README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ tags:
|
|
| 40 |
<td align="center">61.59</td>
|
| 41 |
<td align="center">64.72</td>
|
| 42 |
<td align="center">63.39 | 2.60</td>
|
| 43 |
-
<td align="center">62.
|
| 44 |
<td align="center">63.90 | 3.12</td>
|
| 45 |
</tr>
|
| 46 |
<tr><td colspan="6" align="center"><b>Knowledge</b></td></tr>
|
|
@@ -203,14 +203,14 @@ tags:
|
|
| 203 |
<td align="center">72.69</td>
|
| 204 |
<td align="center">77.25</td>
|
| 205 |
<td align="center">78.24 | 3.43</td>
|
| 206 |
-
<td align="center">
|
| 207 |
<td align="center">74.07 | 6.30</td>
|
| 208 |
</tr>
|
| 209 |
<tr>
|
| 210 |
<td align="left">HumanEval+</td>
|
| 211 |
<td align="center">79.5</td>
|
| 212 |
<td align="center">80.03</td>
|
| 213 |
-
<td align="center">81.
|
| 214 |
<td align="center">80.49 | 12.32</td>
|
| 215 |
<td align="center">82.93 | 7.77</td>
|
| 216 |
</tr>
|
|
@@ -231,14 +231,6 @@ tags:
|
|
| 231 |
<td align="center">34.39 | 4.09</td>
|
| 232 |
</tr>
|
| 233 |
<tr>
|
| 234 |
-
<td align="left">Aider</td>
|
| 235 |
-
<td align="center">55.64</td>
|
| 236 |
-
<td align="center">49.62</td>
|
| 237 |
-
<td align="center">39.85 | 3.57</td>
|
| 238 |
-
<td align="center">43.61 | 8.11</td>
|
| 239 |
-
<td align="center">45.11 | 4.85</td>
|
| 240 |
-
</tr>
|
| 241 |
-
<tr>
|
| 242 |
<td align="left">BIRD-SQL</td>
|
| 243 |
<td align="center">36.11</td>
|
| 244 |
<td align="center">39.67</td>
|
|
@@ -313,14 +305,6 @@ tags:
|
|
| 313 |
<td align="center">73.61 | 5.14</td>
|
| 314 |
</tr>
|
| 315 |
<tr>
|
| 316 |
-
<td align="left">CodeIF-Bench</td>
|
| 317 |
-
<td align="center">50.00</td>
|
| 318 |
-
<td align="center">46.00</td>
|
| 319 |
-
<td align="center">46.00 | 2.62</td>
|
| 320 |
-
<td align="center">42.00 | 6.68</td>
|
| 321 |
-
<td align="center">48.00 | 3.62</td>
|
| 322 |
-
</tr>
|
| 323 |
-
<tr>
|
| 324 |
<td align="left">Nexus FC</td>
|
| 325 |
<td align="center">37.71</td>
|
| 326 |
<td align="center">34.38</td>
|
|
|
|
| 40 |
<td align="center">61.59</td>
|
| 41 |
<td align="center">64.72</td>
|
| 42 |
<td align="center">63.39 | 2.60</td>
|
| 43 |
+
<td align="center">62.07 | 5.34</td>
|
| 44 |
<td align="center">63.90 | 3.12</td>
|
| 45 |
</tr>
|
| 46 |
<tr><td colspan="6" align="center"><b>Knowledge</b></td></tr>
|
|
|
|
| 203 |
<td align="center">72.69</td>
|
| 204 |
<td align="center">77.25</td>
|
| 205 |
<td align="center">78.24 | 3.43</td>
|
| 206 |
+
<td align="center">73.28 | 10.59</td>
|
| 207 |
<td align="center">74.07 | 6.30</td>
|
| 208 |
</tr>
|
| 209 |
<tr>
|
| 210 |
<td align="left">HumanEval+</td>
|
| 211 |
<td align="center">79.5</td>
|
| 212 |
<td align="center">80.03</td>
|
| 213 |
+
<td align="center">81.40 | 5.16</td>
|
| 214 |
<td align="center">80.49 | 12.32</td>
|
| 215 |
<td align="center">82.93 | 7.77</td>
|
| 216 |
</tr>
|
|
|
|
| 231 |
<td align="center">34.39 | 4.09</td>
|
| 232 |
</tr>
|
| 233 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 234 |
<td align="left">BIRD-SQL</td>
|
| 235 |
<td align="center">36.11</td>
|
| 236 |
<td align="center">39.67</td>
|
|
|
|
| 305 |
<td align="center">73.61 | 5.14</td>
|
| 306 |
</tr>
|
| 307 |
<tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 308 |
<td align="left">Nexus FC</td>
|
| 309 |
<td align="center">37.71</td>
|
| 310 |
<td align="center">34.38</td>
|