ResearchDatasetsFigTalkFigTalkFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsNarration Quality EvaluationFigTalk-Gold (D1)76Order Match9GroundingFigTalk-Gold Hard (reference set)74.2Macro F19GroundingFigTalk-Gold Medium (reference set)70.4Macro F19Grounding EvaluationFigTalk Extended84Inputs CF Score8