ResearchTasks3-shot Downstream EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLanguage Model Evaluation Suite (ARC, BoolQ, HSwag, LAMBADA, OBQA, PIQA, Wino)QK-Normed MLA14.18Lambada Perplexity2Jun 16, 2026
Language Model Evaluation Suite (ARC, BoolQ, HSwag, LAMBADA, OBQA, PIQA, Wino)QK-Normed MLA14.18Lambada Perplexity2Jun 16, 2026