ResearchDatasetsBiGGenBiGGenFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPairwise evaluationBIGGEN78.33Human Agreement41Pointwise evaluationBIGGEN0.584Spearman Corr32Direct AssessmentBiGGen-Bench67.69Pearson Correlation Coefficient12