ResearchTasksEvaluation score correlation with ground-truth correctnessEvaluation score correlation with ground-truth correctnessFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated37k questions across 85 domainsLLM-as-a-Judge0.238Pearson's rho18Feb 26, 2026