ResearchDatasetsPopulation-levelFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsModel Repair and RetentionPopulation-level Knowledge & Cognition cohorts (MMLU, TriviaQA, TruthfulQA, ARC-Challenge, GSM8K, IFEval, Math-500, MNLI, HellaSwag)86.9Percent Healed7
Model Repair and RetentionPopulation-level Knowledge & Cognition cohorts (MMLU, TriviaQA, TruthfulQA, ARC-Challenge, GSM8K, IFEval, Math-500, MNLI, HellaSwag)86.9Percent Healed7