ResearchDatasetsMultiple-choice QA BenchmarksMultiple-choice QA BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultiple-choice QAMultiple-choice QA Benchmarks (PIQA, OpenBookQA, HellaSwag, ARC)68.39PIQA Accuracy16
Multiple-choice QAMultiple-choice QA Benchmarks (PIQA, OpenBookQA, HellaSwag, ARC)68.39PIQA Accuracy16