ResearchTasksFew-shot Language EvaluationFew-shot Language EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedARC, HellaSwag, MMLU, TruthfulQA, WinoGrande Few-shot Llama2-7BQLoRA56.06ARC Accuracy6Feb 26, 2026