ResearchTasksPrompt Adherence EvaluationPrompt Adherence EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedDB-3DME 1.0 (test)ChatGPT-5-high0.483Pearson R15Jun 11, 2026