ResearchTasksGoal reconstructionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOneStop (New Item)Incorrect Human (same critical span)0.651BERTScore11Mar 4, 2026OneStop (New Participant & Item)DalEye-Llama54.8Question Word Accuracy11Mar 4, 2026OneStopDalEye-LLaVA54.8Accuracy (Question Word)11Mar 4, 2026OneStop (New Participant)Gemini few-shot71.3QW Accuracy11Mar 4, 2026