@@ -117,9 +117,9 @@ <h3 class="fw-light text-nowrap">
117117            alt ="blog "
118118            class ="img-fluid "
119119        /> </ a > 
120-         < a  href ="https://arxiv.org/html/2406.11927v1  "
120+         < a  href ="https://arxiv.org/abs/2410.01999v1#:~:text=View%20a%20PDF%20of%20the%20paper%20titled%20CodeMMLU:%20A%20Multi-Task  "
121121          > < img 
122-             src ="https://img.shields.io/badge/2406.11927 -red?style=for-the-badge&label=arXiv "
122+             src ="https://img.shields.io/badge/2410.01999 -red?style=for-the-badge&label=arXiv "
123123            alt ="leaderboard "
124124            class ="img-fluid "
125125        /> </ a > 
@@ -131,13 +131,13 @@ <h3 class="fw-light text-nowrap">
131131        /> </ a > 
132132      </ div > 
133133      < div  class ="d-flex flex-row justify-content-center gap-3 "> 
134-         < a  href ="https://github.com/FSoft-AI4Code/RepoExec  "
134+         < a  href ="https://github.com/FSoft-AI4Code/CodeMMLU  "
135135          > < img 
136136            src ="https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white "
137137            alt ="github "
138138            class ="img-fluid "
139139        /> </ a > 
140-         < a  href ="https://github.com/FSoft-AI4Code/RepoExec/blob/master/paper/main.pdf  "
140+         < a  href ="https://arxiv.org/abs/2410.01999v1#:~:text=View%20a%20PDF%20of%20the%20paper%20titled%20CodeMMLU:%20A%20Multi-Task  "
141141          > < img 
142142            src ="https://img.shields.io/badge/📝 paper-%23121011.svg?style=for-the-badge "
143143            alt ="paper "
@@ -175,12 +175,12 @@ <h3>📝 Notes</h3>
175175          < ol > 
176176            < li > 
177177              Evaluated using
178-               < a  href ="https://github.com/FSoft-AI4Code/RepoExec  "
179-                 > RepoExec </ a 
178+               < a  href ="https://github.com/FSoft-AI4Code/CodeMMLU  "
179+                 > CodeMMLU </ a 
180180              > 
181181            </ li > 
182182            < li > 
183-               Models are ranked according to Pass@1  using greedy decoding.
183+               Models are ranked according to Accuracy  using greedy decoding.
184184            </ li > 
185185            <!-- <li> 
186186              <i>Complete</i> vs <i>Instruct</i>: 
@@ -220,6 +220,12 @@ <h3>🤗 More Leaderboards</h3>
220220        benchmarks and leaderboards, such as:
221221        < div  class ="inline-block mt-3 "> 
222222          < ol > 
223+             < li > 
224+               < a 
225+                 href ="https://repoexec.github.io/ "
226+                 > RepoExec Leaderboard</ a 
227+               > 
228+             </ li > 
223229            < li > 
224230              < a 
225231                href ="https://bigcode-bench.github.io/ "
0 commit comments