ResearchDatasetsStrQAStrQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsQuestion AnsweringStrQA84.45Accuracy24Step-level correctness assessmentStrQA (test)39.5PR-AUC22Step-level reasoning verificationStrQA52.7PR-AUC19Common Sense ReasoningStrQA79.65Accuracy6