ResearchDatasetsCMCQRDCMCQRDFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsDifficulty Correlation with LLM LabelsCMCQRD (n=787)0.69Pearson Correlation2Difficulty Correlation with Human PerformanceCMCQRD n=7870.53Pearson Correlation2