ResearchDatasetsBBFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMathematical Reasoning (Coding Tools)BB-Hard63.33Accuracy25Mathematical Reasoning (Coding Tools)BB Easy95.12Accuracy25Abstention in Question AnsweringBB Answer Unknown97.9Abstention F110Agent-task matchingBB NonIID410.04Cumulative Alignment Cost4