Update README.md

README.md

@@ -95,8 +95,8 @@ We did not considered it for our score, but "if" considered those extra 5 questi
       <td>Reported in third-party performance overview; may differ by protocol</td>
     </tr>
     <tr>
-      <td>Stable Code 3B*</td>
-      <td>~32–33 (estimate)</td>
+      <td>Qwen/Qwen3-4B-GGUF (bigger size model)</td>
+      <td>~73%</td>
       <td>Indicative proxy from published code-task performance breakdowns (not a strict HumanEval pass@1)</td>
     </tr>
     <tr>
@@ -105,8 +105,8 @@ We did not considered it for our score, but "if" considered those extra 5 questi
       <td>Indicative proxy from published code-task performance breakdowns (not a strict HumanEval pass@1)</td>
     </tr>
     <tr>
-      <td>StarCoder 3B*</td>
-      <td>~21.6 (estimate)</td>
+      <td>CodeLlama 7B‑Python (bigger size model)</td>
+      <td>~74 % </td>
       <td>Indicative proxy from published code-task performance breakdowns (not a strict HumanEval pass@1)</td>
     </tr>
   </tbody>