Loading problem & solution, please wait...
Hover over tokens in the solution to see which tokens the model attended to when generating the solution. Click a token to select it; clicking in empty space will deselect.
Solutions were selected randomly, keeping at most one correct (passes all test cases in our dataset) and one incorrect sample per problem and language. Note that since our dataset only has a limited number of test cases, passing all tests we have cannot completely rule out false positives (~4%), or solutions that are correct but inefficient (~42%).
Check out selected problems with commentary from World-Class Competitive Programmer Petr Mitrichev: 1566_E 1591_C 1618_B 1618_E 1619_D 1623_B