Update README.md
Browse files
README.md
CHANGED
|
@@ -62,7 +62,8 @@ After intense refining, <b>Nerdsking-python-coder-3B-i</b> has achieved <b>88.41
|
|
| 62 |
<br><b>IMPORTANT:</b> 5 "errors" from the model during the benchmark were mere "import errors" (missing imports: reduce, Optional, List, etc ), but the logic was perfect, therefore:
|
| 63 |
- the model reasoning was right
|
| 64 |
- the failure is syntactic / boilerplate, not conceptual<br>
|
| 65 |
-
|
|
|
|
| 66 |
<hr>
|
| 67 |
|
| 68 |
|
|
|
|
| 62 |
<br><b>IMPORTANT:</b> 5 "errors" from the model during the benchmark were mere "import errors" (missing imports: reduce, Optional, List, etc ), but the logic was perfect, therefore:
|
| 63 |
- the model reasoning was right
|
| 64 |
- the failure is syntactic / boilerplate, not conceptual<br>
|
| 65 |
+
|
| 66 |
+
If considered those extra 5 questions as correct, our benchmark would be <b>much higher</b>.
|
| 67 |
<hr>
|
| 68 |
|
| 69 |
|