ResearchDatasetsNorwegian packNorwegian packFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety EvaluationNorwegian pack (full 36-scenario)43.68Judge-L Score8Instruction-following and safety evaluationNorwegian pack14.2Overall Delta Score4