ResearchTasksSimple Question AnsweringSimple Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPopQA (test)HippoRAG2 + DeepRefine-8B65.24RAG F136May 12, 2026NQ* (test)HippoRAG + DeepRefine-8B40.09RAG F136May 12, 2026PopQAGTE-Qwen2-7B-Instruct56.3F126Jun 30, 2026NQHippoRAG 263.3F1 Score14Jun 30, 2026