ResearchTasksRefusal PredictionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLocked GLM n=4,200, 20 item clusters (test)Llama-3.1-70B-0.475Beta Coefficient4May 8, 2026LoCoMo fullREMem73.3Precision3Feb 26, 2026