ResearchTasksModel Alignment EvaluationModel Alignment EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedStoic Alignment BenchmarkQwen3 Few-shot32.24Mean Score16May 13, 2026Re:Form SFT Evaluation Set (val)14B SFT94.3Validation Rate11Jul 7, 2026