ResearchDatasetsAnthropic model-written-evalsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSycophancy MitigationAnthropic Model-Written Evals0.78Sycophancy Rate45Sycophancy ResistanceAnthropic model-written-evals sycophancy suite94.6Overall Sycophancy Resistance Score6
Sycophancy ResistanceAnthropic model-written-evals sycophancy suite94.6Overall Sycophancy Resistance Score6