🔎 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

model: temp:

def f(string):
    bigTab = 100
    for i in range(10, 30):
        if 0 < string.count('\t') < 20:
            bigTab = i
            break
    return string.expandtabs(bigTab)
assert f('1  \t\t\t3') == '1                             3'

CRUXEval-I assert f(??) == '1 3'

CRUXEval-O assert f('1 \t\t\t3') == ??

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