ResearchDatasetsLanguage Model Evaluation SuiteLanguage Model Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResults3-shot Downstream EvaluationLanguage Model Evaluation Suite (ARC, BoolQ, HSwag, LAMBADA, OBQA, PIQA, Wino)14.18Lambada Perplexity2
3-shot Downstream EvaluationLanguage Model Evaluation Suite (ARC, BoolQ, HSwag, LAMBADA, OBQA, PIQA, Wino)14.18Lambada Perplexity2