ResearchDatasetsGSM8K, ARC-C, MedQA, BoolQ, and CoLAGSM8K, ARC-C, MedQA, BoolQ, and CoLAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-task Language EvaluationGSM8K, ARC-C, MedQA, BoolQ, and CoLA Evaluation Average79.87Average Accuracy14
Multi-task Language EvaluationGSM8K, ARC-C, MedQA, BoolQ, and CoLA Evaluation Average79.87Average Accuracy14