Update README.md

README.md

@@ -46,62 +46,62 @@ language:
     <tr>
       <td style="padding: 8px;"><strong>Konan-LLM-OND</strong></td>
       <td style="text-align: center; padding: 8px;">4.0B</td>
-      <td style="text-align: center; padding: 8px;"><strong>50.6<strong></td>
-      <td style="text-align: center; padding: 8px;"><strong>46.4<strong></td>
-      <td style="text-align: center; padding: 8px;">68.4</td>
-      <td style="text-align: center; padding: 8px;"><strong>68.8<strong></td>
-      <td style="text-align: center; padding: 8px;"><strong>86.8<strong></td>
-      <td style="text-align: center; padding: 8px;">73.3</td>
+      <td style="text-align: center; padding: 8px;"><strong>54.33%<strong></td>
+      <td style="text-align: center; padding: 8px;">53.70%</td>
+      <td style="text-align: center; padding: 8px;">68.42%</td>
+      <td style="text-align: center; padding: 8px;">70.76%</td>
+      <td style="text-align: center; padding: 8px;"><strong>86.66%<strong></td>
+      <td style="text-align: center; padding: 8px;">73.38%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>EXAONE-3.5-2.4B-Instruct</strong></td>
       <td style="text-align: center; padding: 8px;">2.4B</td>
-      <td style="text-align: center; padding: 8px;">44.2</td>
-      <td style="text-align: center; padding: 8px;">31.8</td>
-      <td style="text-align: center; padding: 8px;">60.5</td>
-      <td style="text-align: center; padding: 8px;">59.1</td>
-      <td style="text-align: center; padding: 8px;">81.5</td>
-      <td style="text-align: center; padding: 8px;">77.7</td>
+      <td style="text-align: center; padding: 8px;">45.22%</td>
+      <td style="text-align: center; padding: 8px;">38.55%</td>
+      <td style="text-align: center; padding: 8px;">60.53%</td>
+      <td style="text-align: center; padding: 8px;">61.76%</td>
+      <td style="text-align: center; padding: 8px;">78.54%</td>
+      <td style="text-align: center; padding: 8px;">77.73%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>kanana-1.5-2.1b-instruct-2505</strong></td>
       <td style="text-align: center; padding: 8px;">2.1B</td>
-      <td style="text-align: center; padding: 8px;">32.7</td>
-      <td style="text-align: center; padding: 8px;">27.2</td>
-      <td style="text-align: center; padding: 8px;">56.0</td>
-      <td style="text-align: center; padding: 8px;">52.9</td>
-      <td style="text-align: center; padding: 8px;">68.8</td>
-      <td style="text-align: center; padding: 8px;">64.6</td>
+      <td style="text-align: center; padding: 8px;">38.14%</td>
+      <td style="text-align: center; padding: 8px;">34.14%</td>
+      <td style="text-align: center; padding: 8px;">55.99%</td>
+      <td style="text-align: center; padding: 8px;">55.25%</td>
+      <td style="text-align: center; padding: 8px;">74.83%</td>
+      <td style="text-align: center; padding: 8px;">64.60%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>Midm-2.0-Mini-Instruct</strong></td>
       <td style="text-align: center; padding: 8px;">2.3B</td>
-      <td style="text-align: center; padding: 8px;">42.4</td>
-      <td style="text-align: center; padding: 8px;">36.2</td>
-      <td style="text-align: center; padding: 8px;">66.8</td>
-      <td style="text-align: center; padding: 8px;">57.4</td>
-      <td style="text-align: center; padding: 8px;">74.8</td>
-      <td style="text-align: center; padding: 8px;">68.3</td>
+      <td style="text-align: center; padding: 8px;">43.24%</td>
+      <td style="text-align: center; padding: 8px;">37.30%</td>
+      <td style="text-align: center; padding: 8px;">66.81%</td>
+      <td style="text-align: center; padding: 8px;">55.62%</td>
+      <td style="text-align: center; padding: 8px;">72.55%</td>
+      <td style="text-align: center; padding: 8px;">68.30%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>Qwen3-4B(w/o reasoning)</strong></td>
       <td style="text-align: center; padding: 8px;">4.0B</td>
-      <td style="text-align: center; padding: 8px;">-(*)</td>
-      <td style="text-align: center; padding: 8px;">37.5</td>
-      <td style="text-align: center; padding: 8px;">68.4</td>
-      <td style="text-align: center; padding: 8px;">-(*)</td>
-      <td style="text-align: center; padding: 8px;">83.9</td>
-      <td style="text-align: center; padding: 8px;"><strong>80.0<strong></td>
+      <td style="text-align: center; padding: 8px;">52.55%</td>
+      <td style="text-align: center; padding: 8px;"><strong>54.16%<strong></td>
+      <td style="text-align: center; padding: 8px;">68.42%</td>
+      <td style="text-align: center; padding: 8px;"><strong>71.81%<strong></td>
+      <td style="text-align: center; padding: 8px;">76.57%</td>
+      <td style="text-align: center; padding: 8px;"><strong>80.04%<strong></td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>gemma-3-4b-it</strong></td>
       <td style="text-align: center; padding: 8px;">4.3B</td>
-      <td style="text-align: center; padding: 8px;">38.7</td>
-      <td style="text-align: center; padding: 8px;">32.7</td>
-      <td style="text-align: center; padding: 8px;"><strong>69.2<strong></td>
-      <td style="text-align: center; padding: 8px;">59.1</td>
-      <td style="text-align: center; padding: 8px;">82.2</td>
-      <td style="text-align: center; padding: 8px;">78.3</td>
+      <td style="text-align: center; padding: 8px;">40.10%</td>
+      <td style="text-align: center; padding: 8px;">43.88%</td>
+      <td style="text-align: center; padding: 8px;"><strong>69.15%<strong></td>
+      <td style="text-align: center; padding: 8px;">61.25%</td>
+      <td style="text-align: center; padding: 8px;">83.24%</td>
+      <td style="text-align: center; padding: 8px;">78.28%</td>
     </tr>
   </tbody>
 </table>
@@ -129,83 +129,88 @@ language:
     <tr>
       <td style="padding: 8px;"><strong>Konan-LLM-OND</strong></td>
       <td style="text-align: center; padding: 8px;">4.0B</td>
-      <td style="text-align: center; padding: 8px;">50.6</td>
-      <td style="text-align: center; padding: 8px;"><strong>46.4</strong></td>
-      <td style="text-align: center; padding: 8px;">68.4</td>
-      <td style="text-align: center; padding: 8px;">68.8</td>
-      <td style="text-align: center; padding: 8px;">86.8</td>
-      <td style="text-align: center; padding: 8px;">73.3</td>
+      <td style="text-align: center; padding: 8px;">54.33%</td>
+      <td style="text-align: center; padding: 8px;">53.70%</td>
+      <td style="text-align: center; padding: 8px;">68.42%</td>
+      <td style="text-align: center; padding: 8px;">70.55%</td>
+      <td style="text-align: center; padding: 8px;">86.66%</td>
+      <td style="text-align: center; padding: 8px;">73.38%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>A.X-4.0-Light</strong></td>
       <td style="text-align: center; padding: 8px;">7.2B</td>
-      <td style="text-align: center; padding: 8px;"><strong>55.3</strong></td>
-      <td style="text-align: center; padding: 8px;">44.6</td>
-      <td style="text-align: center; padding: 8px;">71.5</td>
-      <td style="text-align: center; padding: 8px;"><strong>70.6</strong></td>
-      <td style="text-align: center; padding: 8px;">87.3</td>
-      <td style="text-align: center; padding: 8px;">81.3</td>
+      <td style="text-align: center; padding: 8px;"><strong>62.48%</strong></td>
+      <td style="text-align: center; padding: 8px;">51.08%</td>
+      <td style="text-align: center; padding: 8px;">71.49%</td>
+      <td style="text-align: center; padding: 8px;">73.15%</td>
+      <td style="text-align: center; padding: 8px;">86.58%</td>
+      <td style="text-align: center; padding: 8px;">81.33%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>EXAONE-3.5-7.8B-Instruct</strong></td>
       <td style="text-align: center; padding: 8px;">7.8B</td>
-      <td style="text-align: center; padding: 8px;">48.0</td>
-      <td style="text-align: center; padding: 8px;">39.3</td>
-      <td style="text-align: center; padding: 8px;">66.8</td>
-      <td style="text-align: center; padding: 8px;">66.8</td>
-      <td style="text-align: center; padding: 8px;"><strong>91.4</strong></td>
-      <td style="text-align: center; padding: 8px;">79.9</td>
+      <td style="text-align: center; padding: 8px;">53.03%</td>
+      <td style="text-align: center; padding: 8px;">48.02</td>
+      <td style="text-align: center; padding: 8px;">66.81%</td>
+      <td style="text-align: center; padding: 8px;">71.43%</td>
+      <td style="text-align: center; padding: 8px;"><strong>89.46%</strong></td>
+      <td style="text-align: center; padding: 8px;">79.85%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>kanana-1.5-8b-instruct-2505</strong></td>
       <td style="text-align: center; padding: 8px;">8.0B</td>
-      <td style="text-align: center; padding: 8px;">40.4</td>
-      <td style="text-align: center; padding: 8px;">35.5</td>
-      <td style="text-align: center; padding: 8px;">71.1</td>
-      <td style="text-align: center; padding: 8px;">63.1</td>
-      <td style="text-align: center; padding: 8px;">79.3</td>
-      <td style="text-align: center; padding: 8px;">76.8</td>
+      <td style="text-align: center; padding: 8px;">47.80%</td>
+      <td style="text-align: center; padding: 8px;">39.65%</td>
+      <td style="text-align: center; padding: 8px;">71.05%</td>
+      <td style="text-align: center; padding: 8px;">65.90%</td>
+      <td style="text-align: center; padding: 8px;">76.57%</td>
+      <td style="text-align: center; padding: 8px;">76.80%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>Midm-2.0-Base-Instruct</strong></td>
       <td style="text-align: center; padding: 8px;">11.5B</td>
-      <td style="text-align: center; padding: 8px;">54.2</td>
-      <td style="text-align: center; padding: 8px;">46.0</td>
-      <td style="text-align: center; padding: 8px;"><strong>75.0</strong></td>
-      <td style="text-align: center; padding: 8px;">70.2</td>
-      <td style="text-align: center; padding: 8px;">88.9</td>
-      <td style="text-align: center; padding: 8px;">79.7</td>
+      <td style="text-align: center; padding: 8px;">58.43%</td>
+      <td style="text-align: center; padding: 8px;">51.18%</td>
+      <td style="text-align: center; padding: 8px;"><strong>75.00%</strong></td>
+      <td style="text-align: center; padding: 8px;">71.84%</td>
+      <td style="text-align: center; padding: 8px;">79.83%</td>
+      <td style="text-align: center; padding: 8px;">79.67%</td>
     </tr>
     <tr>
       <td style="padding: 8px;"><strong>Qwen3-8B(w/o reasoning)</strong></td>
       <td style="text-align: center; padding: 8px;">8.1B</td>
-      <td style="text-align: center; padding: 8px;">-(*)</td>
-      <td style="text-align: center; padding: 8px;">40.0</td>
-      <td style="text-align: center; padding: 8px;">70.9</td>
-      <td style="text-align: center; padding: 8px;">-(*)</td>
-      <td style="text-align: center; padding: 8px;">84.0</td>
-      <td style="text-align: center; padding: 8px;"><strong>82.8</strong></td>
+      <td style="text-align: center; padding: 8px;">57.43%</td>
+      <td style="text-align: center; padding: 8px;"><strong>57.88%<strong></td>
+      <td style="text-align: center; padding: 8px;">70.91%</td>
+      <td style="text-align: center; padding: 8px;"><strong>76.45%<strong></td>
+      <td style="text-align: center; padding: 8px;">77.79%</td>
+      <td style="text-align: center; padding: 8px;"><strong>82.81%</strong></td>
     </tr>
   </tbody>
 </table>
 
 Note:
 * The highest scores are shown in bold.
-* (*) Qwen3 models often failed to strictly follow the required answer format in the few-shot setting, which made the scores unreliable. After correcting the evaluation pipeline, we will update the scores.
 
 ## **Benchmark Setup**
 
 All benchmarks were executed using the following standardized environment.
 
 * **Evaluation Framework**: `lm-evaluation-harness v0.4.9`
-* **Runtime & Hardware**: All models were served with `vLLM v0.9.1` on a single NVIDIA GPU.
+* **Runtime & Hardware**: All models were served with `vLLM v0.9.2` on NVIDIA GPU.
 * **Inference Mode**: For every benchmark, we invoked the `chat_completions` API, and scores were computed solely from the generated responses.
 
 #### **Metric Adjustments**
 
-* KMMLU was evaluated using the "kmmlu_direct" task in the lm-evaluation-harness.
-* MMLU was run with the same configuration as "kmmlu_direct".
-* Ko-IFEval was evaluated using the original IFEval protocol, with the dataset sourced from [allganize/IFEval-Ko](https://huggingface.co/datasets/allganize/IFEval-Ko).
+* **KMMLU** was evaluated in a zero-shot setting using a CoT-style prompt modified from the `kmmlu_direct` task in lm-evaluation-harness, with enhanced preprocessing filters applied during evaluation.
+
+* **MMLU** was evaluated in a zero-shot setting using a CoT-style prompt modified from the `mmlu_generative` task in lm-evaluation-harness, with enhanced preprocessing filters applied during evaluation.
+
+* **GSM8K** was evaluated in a zero-shot setting using the original prompt format from lm-evaluation-harness, with enhanced preprocessing filters applied.
+
+* **HRM8K** was evaluated in a zero-shot setting using the original prompt and data format from lm-evaluation-harness, without any modifications. 
+
+* **Ko-IFEval** was evaluated in a zero-shot setting using the original **IFEval** protocol, with the dataset sourced from [allganize/IFEval-Ko](https://huggingface.co/datasets/allganize/IFEval-Ko).
 
 #### **Evaluation Protocol**
 
@@ -221,12 +226,12 @@ All benchmarks were executed using the following standardized environment.
     <tr>
       <td><strong>KMMLU</strong></td>
       <td><code>exact_match</code></td>
-      <td>5-shot</td>
+      <td>0-shot CoT</td>
     </tr>
     <tr>
       <td><strong>HRM8K</strong></td>
       <td>mean of <code>hrm8k_gsm8k</code>, <code>hrm8k_ksm</code>, <code>hrm8k_math</code>, <code>hrm8k_mmmlu</code>, <code>hrm8k_omni_math</code></td>
-      <td>5-shot</td>
+      <td>0-shot</td>
     </tr>
     <tr>
       <td><strong>Ko-IFEval</strong></td>
@@ -236,12 +241,12 @@ All benchmarks were executed using the following standardized environment.
     <tr>
       <td><strong>MMLU</strong></td>
       <td><code>exact_match</code></td>
-      <td>5-shot</td>
+      <td>0-shot CoT</td>
     </tr>
     <tr>
       <td><strong>GSM8K</strong></td>
-      <td><code>exact_match</code> &amp; <code>flexible-extract</code></td>
-      <td>5-shot</td>
+      <td><code>flexible-extract</code></td>
+      <td>0-shot</td>
     </tr>
     <tr>
       <td><strong>IFEval</strong></td>