ResearchTasksDiscriminative TaskFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRPEval Implicit Memory, Multi-PreferenceGPT-4.1 + RP-Reasoner0.44IA (Macro)16Feb 26, 2026RPEval Implicit Memory, Single-PreferenceQwen2.5-7B0.02Ignorance Score16Feb 26, 2026POPE MSCOCO (test)ICD87.51Random Accuracy15Feb 26, 2026AMBER Discrimination 1.0 (test)Octopus76.7Accuracy10Feb 26, 2026AMBERMESA84.3Accuracy4Apr 10, 2026