ResearchTasksSycophancy AssessmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedBASIL 1.0 (Under-Update)mistral:7b-0.355Change in Bayesian Error (RMSE)32Apr 21, 2026BASIL Over-Update 1.0claude-haiku-4-50.016Change in Bayesian Error (RMSE)32Apr 21, 2026BASIL 1.0 (All)gpt-4o-mini-0.096Change in Bayesian Error (RMSE)32Apr 21, 2026