ResearchDatasetsFoundational Benchmarks SuiteFoundational Benchmarks SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-task Language UnderstandingFoundational Benchmarks Suite (HS, PIQA, SIQA, Wino, MMLU, NQ, TQA, ARC-C, ARC-E, OBQA, BoolQ, DROP, BBH, GSM8K)60.1Average Accuracy13
Multi-task Language UnderstandingFoundational Benchmarks Suite (HS, PIQA, SIQA, Wino, MMLU, NQ, TQA, ARC-C, ARC-E, OBQA, BoolQ, DROP, BBH, GSM8K)60.1Average Accuracy13