SOTA Multi-hop Question Answering benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
2WikiMultiHopQA	CoopRAG	EM71.7	278	2d ago
HotpotQA	ARISE	F1 Score75.39	221	2d ago
HotpotQA (test)		F180.79	198	2d ago
2WikiMQA	CIRAG	F1 Score76.4	154	3d ago
2WikiMultiHopQA (test)	QuCo-RAG	EM64.6	143	3d ago
MuSiQue (test)	MultiCube-RAG	F150.9	111	3d ago
Musique	ARISE	EM40.5	106	2d ago
Bamboogle	Agentic-R	Exact Match48	97	3d ago
HotpotQA	CIRAG	F174.9	79	3d ago
2WikiMultiHopQA Out-Of-Distribution (OOD)	QwenLong-L1-32B	Accuracy74.2	72	3d ago
LoCoMo	Membox	F148.35	67	2d ago
Multi-hop RAG	IndexLM-4B	F186.07	65	3d ago
HotpotQA fullwiki setting (test)	IDRQA	Answer F175.9	64	3d ago
HotpotQA	Agentic-R	Exact Match (EM)47.68	56	3d ago
2WikiMHQA	CRAFT7B	F1 Score85.56	55	2d ago
Bamboogle	TC+FM*	Accuracy75.2	52	3d ago
HotpotQA	ACPS	F175.97	48	3d ago
Bamboogle (test)	Workflow-R1-Search	EM57.6	46	3d ago
Multi-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle) (test)	JADE	HotpotQA Score57.02	44	3d ago
HotpotQA (dev)	SEQGRAPH	Answer F181.62	43	3d ago
2Wiki	ChainRAG (CxtInt)	F1 Score70.58	41	3d ago
HotpotQA	Stable-RAG	SubEM39.12	40	3d ago
Multi-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle)	Search-R1-GRPO + LLDS	HotpotQA Score49.2	39	3d ago
HotpotQA fullwiki setting (dev)	PATHFID+	Answer F181.5	38	3d ago
Bamboogle	GraphAnchor	EM32.23	37	3d ago

Showing 25 of 189 rows

...