Merge branch 'llama3' of github.com:lm-sys/lm-sys.github.io into llama3

blog/2024-05-01-llama3.md

@@ -117,20 +117,19 @@ td {text-align: left}
 <table style="display: flex; justify-content: center;">
 <tbody>
 <tr>
-<th>Model</th> <th>Battles</th> <th>Unique Judges</th> <th>Mean Votes per Judge</th> <th>Median Votes per Judge</th> <th>Max Votes per Judge</th> <th>Mean Judge Age</th> <th>Median Judge Age</th> <th>Max Judge Age</th>
+<th>Model</th> <th>Battles</th> <th>Unique Judges</th> <th>Mean Votes per Judge</th> <th>Median Votes per Judge</th> <th>Max Votes per Judge</th>
 </tr>
 <tr>
-<td>Llama 3-70B-Instruct</td> <td>12,719</td> <td>7,591</td> <td>1.68</td> <td>1</td> <td>65</td> <td>1 hr 10 min</td> <td>2 hr 12 min</td> <td>2 days</td>
+<td>Llama 3-70B-Instruct</td> <td>12,719</td> <td>7,591</td> <td>1.68</td> <td>1</td> <td>65</td>
 </tr>
 <tr>
-<td>Claude-3-opus-20240229</td> <td>68,656</td> <td>48,570</td> <td>1.41</td> <td>1</td> <td>73</td> <td>1 hr 57 min</td> <td>1 hr 55 min</td> <td>3 days</td>
+<td>Claude-3-opus-20240229</td> <td>68,656</td> <td>48,570</td> <td>1.41</td> <td>1</td> <td>73</td>
 </tr>
 <tr>
-<td>All Models All Time</td> <td>749,205</td> <td>316,372</td> <td>2.37</td> <td>1</td> <td>591</td> <td>8 hr 27 min</td> <td>2 hr 23 min</td> <td>295 days</td>
+<td>All Models All Time</td> <td>749,205</td> <td>316,372</td> <td>2.37</td> <td>1</td> <td>591</td>
 </tr>
 </tbody>
 </table>
-<p>*Judge age is defined as rating_date - min_rating_date(ip_address)</p>
 
 
 In order to limit the impact of user’s that vote many times we can take the mean of each judge’s win rate, thereby bounding the impact of each individual judge. In this case, we find this stratified win rate shown in Table 3 is still very similar to the original winrate, suggesting that very active judges are not skewing the result.