ResearchTasksPersonalized LLM Alignment EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPersonalRewardBench (test)Llama3.1-8B-Instruct-GRPO3.354Mean Score6Feb 26, 2026