ResearchDatasetsBABABENCHFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLogic puzzle reasoningBABABENCH Tier 37,800Success Rate (SR)23Logic puzzle reasoningBABABENCH Tier 282.22Success Rate23Logic puzzle reasoningBABABENCH Tier 195.56Success Rate23