Slim Frikha commited on
Commit
2d89dec
·
verified ·
1 Parent(s): c2b78c8

fix rounding typos

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -161,9 +161,9 @@ We report in the following table our internal pipeline benchmarks.
161
  </tr>
162
  <tr>
163
  <td>GPQA (0-shot)</td>
164
- <td><b>33.6</b></td>
165
- <td>31.9</td>
166
  <td>32</td>
 
167
  </tr>
168
  <tr>
169
  <td>GPQA (0-shot, COT)</td>
@@ -174,13 +174,13 @@ We report in the following table our internal pipeline benchmarks.
174
  <tr>
175
  <td>MUSR (0-shot)</td>
176
  <td>38.6</td>
177
- <td>40.7</td>
178
  <td><b>46.4</b></td>
179
  </tr>
180
  <tr>
181
  <td>BBH (3-shot)</td>
182
  <td>48.6</td>
183
- <td><b>54.2</b></td>
184
  <td>52.4</td>
185
  </tr>
186
  <tr>
 
161
  </tr>
162
  <tr>
163
  <td>GPQA (0-shot)</td>
164
+ <td><b>33.5</b></td>
 
165
  <td>32</td>
166
+ <td>31.9</td>
167
  </tr>
168
  <tr>
169
  <td>GPQA (0-shot, COT)</td>
 
174
  <tr>
175
  <td>MUSR (0-shot)</td>
176
  <td>38.6</td>
177
+ <td>41</td>
178
  <td><b>46.4</b></td>
179
  </tr>
180
  <tr>
181
  <td>BBH (3-shot)</td>
182
  <td>48.6</td>
183
+ <td><b>54.1</b></td>
184
  <td>52.4</td>
185
  </tr>
186
  <tr>