ResearchDatasetsSQuAD, HellaSwag, and HeadQASQuAD, HellaSwag, and HeadQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLLM Query RoutingSQuAD, HellaSwag, and HeadQA (out-of-domain)89Accuracy11