Update README.md

README.md

@@ -119,6 +119,184 @@ print(tokenizer.decode(outputs[0]))
 
 # Evaluation
 
+<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
+    <colgroup>
+        <col style="width: 10%;">
+        <col style="width: 10%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
+    </colgroup>
+    <thead>
+        <tr>
+            <th>Category</th>
+            <th>Benchmark</th>
+            <th>Llama3.1-8B</th>
+            <th>Qwen2-7B</th>
+            <th>Qwen2.5-7B</th>
+            <th>Falcon3-7B-Base</th>
+            <th>Gemma2-9B</th>
+            <th>Yi1.5-9B</th>
+            <th>Mistral-NeMo-12B</th>
+            <th>Falcon3-10B-Base</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td rowspan="3">General</td>
+            <td>MMLU (5-shot)</td>
+            <td>65.2</td>
+            <td>70.4</td>
+            <td>74.2</td>
+            <td>67.5</td>
+            <td>0</td>
+            <td>69.6</td>
+            <td>68.8</td>
+            <td>73.1</td>
+        </tr>
+        <tr>
+            <td>MMLU-PRO (5-shot)</td>
+            <td>32.7</td>
+            <td>42.1</td>
+            <td>43.5</td>
+            <td>39.2</td>
+            <td>0</td>
+            <td>39.3</td>
+            <td>34.7</td>
+            <td>42.5</td>
+        </tr>
+        <tr>
+            <td>IFEval</td>
+            <td>12.0</td>
+            <td>30.6</td>
+            <td>33.9</td>
+            <td>34.3</td>
+            <td>0</td>
+            <td>29.1</td>
+            <td>16.1</td>
+            <td>36.4</td>
+        </tr>
+        <tr>
+            <td rowspan="2">Math</td>
+            <td>GSM8K (5-shot)</td>
+            <td>49.4</td>
+            <td>77.9</td>
+            <td>82.9</td>
+            <td>76.2</td>
+            <td>69.1</td>
+            <td>63.8</td>
+            <td>55.3</td>
+            <td>81.4</td>
+        </tr>
+        <tr>
+            <td>MATH(4-shot)</td>
+            <td>4.1</td>
+            <td>17.5</td>
+            <td>15.5</td>
+            <td>18.0</td>
+            <td>0</td>
+            <td>9.2</td>
+            <td>4.9</td>
+            <td>22.9</td>
+        </tr>
+        <tr>
+            <td rowspan="4">Reasoning</td>
+            <td>Arc Challenge (25-shot)</td>
+            <td>53.4</td>
+            <td>57.4</td>
+            <td>59.0</td>
+            <td>59.6</td>
+            <td>63.7</td>
+            <td>58.2</td>
+            <td>60.6</td>
+            <td>62.6</td>
+        </tr>
+        <tr>
+            <td>GPQA (0-shot)</td>
+            <td>31.0</td>
+            <td>31.9</td>
+            <td>33.0</td>
+            <td>35.5</td>
+            <td>0</td>
+            <td>36.6</td>
+            <td>28.8</td>
+            <td>34.1</td>
+        </tr>
+        <tr>
+            <td>MUSR (0-shot)</td>
+            <td>38.0</td>
+            <td>44.1</td>
+            <td>44.2</td>
+            <td>47.3</td>
+            <td>0</td>
+            <td>43.3</td>
+            <td>39.2</td>
+            <td>44.2</td>
+        </tr>
+        <tr>
+            <td>BBH (3-shot)</td>
+            <td>46.5</td>
+            <td>53.3</td>
+            <td>54.0</td>
+            <td>51.0</td>
+            <td>0</td>
+            <td>51.3</td>
+            <td>50.2</td>
+            <td>59.7</td>
+        </tr>
+        <tr>
+            <td rowspan="4">CommonSense Understanding</td>
+            <td>PIQA (0-shot)</td>
+            <td>80.3</td>
+            <td>79.8</td>
+            <td>78.7</td>
+            <td>77.7</td>
+            <td>81.4</td>
+            <td>79.8</td>
+            <td>81.4</td>
+            <td>79.1</td>
+        </tr>
+        <tr>
+            <td>SciQ (0-shot)</td>
+            <td>96.3</td>
+            <td>95.9</td>
+            <td>96.6</td>
+            <td>95.3</td>
+            <td>97.2</td>
+            <td>95.8</td>
+            <td>96.4</td>
+            <td>96.0</td>
+        </tr>
+        <tr>
+            <td>Winogrande (0-shot)</td>
+            <td>74.0</td>
+            <td>72.1</td>
+            <td>72.9</td>
+            <td>71.0</td>
+            <td>74.2</td>
+            <td>72.7</td>
+            <td>73.2</td>
+            <td>73.6</td>
+        </tr>
+        <tr>
+            <td>OpenbookQA (0-shot)</td>
+            <td>33.4</td>
+            <td>35.2</td>
+            <td>33.6</td>
+            <td>31.4</td>
+            <td>34.0</td>
+            <td>35.4</td>
+            <td>36.4</td>
+            <td>34.0</td>
+        </tr>
+    </tbody>
+</table>
+
 
 
 # Citation