Research domain
Retrieval & Search (RAG)
Retrieval580 benchmarks · 293 papersInformation Retrieval538 benchmarks · 275 papersMulti-hop Question Answering507 benchmarks · 373 papersImage Retrieval380 benchmarks · 253 papersText-to-Image Retrieval284 benchmarks · 293 papersImage-to-Text Retrieval271 benchmarks · 269 papersGenerative Modeling227 benchmarks · 111 papersText-to-Video Retrieval168 benchmarks · 179 papersOpen-domain Question Answering167 benchmarks · 121 papersRetrieval-Augmented Generation116 benchmarks · 55 papersDocument Retrieval115 benchmarks · 66 papersTable Question Answering111 benchmarks · 80 papersRanking96 benchmarks · 54 papersImage-Text Retrieval95 benchmarks · 93 papersReranking89 benchmarks · 40 papersRoot Cause Analysis86 benchmarks · 13 papersLong-context retrieval79 benchmarks · 54 papersKnowledge Base Question Answering69 benchmarks · 47 papersCross-modal retrieval64 benchmarks · 32 papersText Retrieval60 benchmarks · 82 papersMultimodal Retrieval54 benchmarks · 35 papersTool Retrieval54 benchmarks · 16 papersQuery Routing52 benchmarks · 5 papersGeneral Question Answering43 benchmarks · 27 papersVisual document retrieval42 benchmarks · 23 papersAgentic Search41 benchmarks · 14 papersEvidence Retrieval41 benchmarks · 17 papersMulti-hop QA41 benchmarks · 29 papersOpen-ended Question Answering41 benchmarks · 25 papersSingle-hop Question Answering40 benchmarks · 48 papersKnowledge retrieval39 benchmarks · 20 papersGenerative Retrieval37 benchmarks · 15 papers