ResearchDatasetsGSM8K, Code, LogiQA, Alpaca, UChatGSM8K, Code, LogiQA, Alpaca, UChatFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsForgetting analysisGSM8K, Code, LogiQA, Alpaca, UChat (test)4.8GSM8K Forgetting Rate15