alexmarques commited on
Commit
2080a0e
·
verified ·
1 Parent(s): 52a1be3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -163,6 +163,26 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
163
  <td><strong>Recovery</strong>
164
  </td>
165
  </tr>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  <tr>
167
  <td>GSM-8K (CoT, 8-shot, strict-match)
168
  </td>
 
163
  <td><strong>Recovery</strong>
164
  </td>
165
  </tr>
166
+ <tr>
167
+ <td>MMLU (CoT, 0-shot)
168
+ </td>
169
+ <td>88.11
170
+ </td>
171
+ <td>87.42
172
+ </td>
173
+ <td>99.2%
174
+ </td>
175
+ </tr>
176
+ <tr>
177
+ <td>ARC Challenge (0-shot)
178
+ </td>
179
+ <td>94.97
180
+ </td>
181
+ <td>94.62
182
+ </td>
183
+ <td>99.6%
184
+ </td>
185
+ </tr>
186
  <tr>
187
  <td>GSM-8K (CoT, 8-shot, strict-match)
188
  </td>