🔎 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):
    for i in range(len(text)):
        if text[i] == text[i].upper() and text[i-1].islower():
            return True
    return False
assert f('jh54kkk6') == True
CRUXEval-I 
assert f(??) == True
 

            		
          

          

            
              CRUXEval-O
              
assert f('jh54kkk6') == ??

              

              

            		
          

        

      


      
      

      

        
        
        
        

          330 / 800
        

      


      
      

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