Update README.md
Browse files
README.md
CHANGED
@@ -413,11 +413,11 @@ evalplus.evaluate \
|
|
413 |
<tr>
|
414 |
<td>GSM-8K (5-shot, strict-match)
|
415 |
</td>
|
416 |
-
<td>
|
417 |
</td>
|
418 |
-
<td>
|
419 |
</td>
|
420 |
-
<td>101.
|
421 |
</td>
|
422 |
</tr>
|
423 |
<tr>
|
@@ -453,9 +453,9 @@ evalplus.evaluate \
|
|
453 |
<tr>
|
454 |
<td><strong>Average</strong>
|
455 |
</td>
|
456 |
-
<td><strong>
|
457 |
</td>
|
458 |
-
<td><strong>
|
459 |
</td>
|
460 |
<td><strong>99.5%</strong>
|
461 |
</td>
|
|
|
413 |
<tr>
|
414 |
<td>GSM-8K (5-shot, strict-match)
|
415 |
</td>
|
416 |
+
<td>58.68
|
417 |
</td>
|
418 |
+
<td>59.59
|
419 |
</td>
|
420 |
+
<td>101.6%
|
421 |
</td>
|
422 |
</tr>
|
423 |
<tr>
|
|
|
453 |
<tr>
|
454 |
<td><strong>Average</strong>
|
455 |
</td>
|
456 |
+
<td><strong>75.03</strong>
|
457 |
</td>
|
458 |
+
<td><strong>74.63</strong>
|
459 |
</td>
|
460 |
<td><strong>99.5%</strong>
|
461 |
</td>
|