Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -246,8 +246,8 @@ with tab1:
|
|
| 246 |
<th>Tier</th>
|
| 247 |
<th>Rank</th>
|
| 248 |
<th>Model</th>
|
| 249 |
-
<th
|
| 250 |
-
<th
|
| 251 |
<th>Avg. # Tokens</th>
|
| 252 |
<th>Avg. # Units</th>
|
| 253 |
<th>Avg. # Undecidable</th>
|
|
@@ -263,8 +263,8 @@ with tab1:
|
|
| 263 |
<tr>
|
| 264 |
<th>Rank</th>
|
| 265 |
<th>Model</th>
|
| 266 |
-
<th
|
| 267 |
-
<th
|
| 268 |
<th>Avg. # Tokens</th>
|
| 269 |
<th>Avg. # Units</th>
|
| 270 |
<th>Avg. # Undecidable</th>
|
|
|
|
| 246 |
<th>Tier</th>
|
| 247 |
<th>Rank</th>
|
| 248 |
<th>Model</th>
|
| 249 |
+
<th>🎯 Factual Precision</th>
|
| 250 |
+
<th>🌀 Hallucination Score</th>
|
| 251 |
<th>Avg. # Tokens</th>
|
| 252 |
<th>Avg. # Units</th>
|
| 253 |
<th>Avg. # Undecidable</th>
|
|
|
|
| 263 |
<tr>
|
| 264 |
<th>Rank</th>
|
| 265 |
<th>Model</th>
|
| 266 |
+
<th>🎯 Factual Precision</th>
|
| 267 |
+
<th>🌀 Hallucination Score</th>
|
| 268 |
<th>Avg. # Tokens</th>
|
| 269 |
<th>Avg. # Units</th>
|
| 270 |
<th>Avg. # Undecidable</th>
|