ResearchTasksPrompt-heavy Aggregate Performance EvaluationPrompt-heavy Aggregate Performance EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPrompt-heavy Aggregate qasper, multi_news, hotpotqa, musique, 2wikimqaCASK64.81Weighted Top-14Apr 14, 2026
Prompt-heavy Aggregate qasper, multi_news, hotpotqa, musique, 2wikimqaCASK64.81Weighted Top-14Apr 14, 2026