ResearchTasksDiscriminative ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRPEval Multi-MICRO Explicit MemoryGPT-5 + RP-Reasoner0.71IA Score16Feb 26, 2026RPEval Multi-MACRO, Explicit MemoryQwen2.5-7B + RP-Reasoner0.4IA Score16Feb 26, 2026RPEval Single, Explicit MemoryQwen2.5-7B0.02Ignorance Score16Feb 26, 2026