ResearchDatasetsDownstream NLP BenchmarksDownstream NLP BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot Downstream ReasoningDownstream NLP Benchmarks PIQA, HellaSwag, WinoGrade, OpenBookQA, BoolQA, SciQ, ARC-E, ARC-C, COPA, MMLU76.82PIQA Accuracy4
Zero-shot Downstream ReasoningDownstream NLP Benchmarks PIQA, HellaSwag, WinoGrade, OpenBookQA, BoolQA, SciQ, ARC-E, ARC-C, COPA, MMLU76.82PIQA Accuracy4