ResearchDatasetsGSM8K, GSM-Hard, MATH, StrategyQA, Bamboogle, Coin, Letter, LB, HeadlineGSM8K, GSM-Hard, MATH, StrategyQA, Bamboogle, Coin, Letter, LB, HeadlineFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoningGSM8K, GSM-Hard, MATH, StrategyQA, Bamboogle, Coin, Letter, LB, Headline (test)92.6GSM8K Accuracy15
ReasoningGSM8K, GSM-Hard, MATH, StrategyQA, Bamboogle, Coin, Letter, LB, Headline (test)92.6GSM8K Accuracy15