🔎 CRUXEval Sample Explorer 🔎

CRUXEval is a benchmark complementary to HumanEval and MBPP measuring code reasoning, understanding, and execution capabilities!

Homepage Paper Code HF Dataset Leaderboard

    
def f(text, suffix):
    if suffix and suffix[-1] in text:
        return f(text.rstrip(suffix[-1]), suffix[:-1])
    else:
        return text
assert f('rpyttc', 'cyt') == 'rpytt'
CRUXEval-I 
assert f(??) == 'rpytt'
 

            		
          

          

            
              CRUXEval-O
              
assert f('rpyttc', 'cyt') == ??

              

              

            		
          

        

      


      
      

      

        
        
        
        

          692 / 800
        

      


      
      

        The site is inspired by and based on
        Minerva sample explorer and
        Llemma. Thanks!