ResearchDatasetsHotpotQA, IFBench, HoVer, PUPA, AIME, and LiveBench-MathHotpotQA, IFBench, HoVer, PUPA, AIME, and LiveBench-MathFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPrompt OptimizationHotpotQA, IFBench, HoVer, PUPA, AIME, and LiveBench-Math 2018-2025 (test)69HotpotQA Score8
Prompt OptimizationHotpotQA, IFBench, HoVer, PUPA, AIME, and LiveBench-Math 2018-2025 (test)69HotpotQA Score8