# Multi-hop

Source: [Multi-hop](<https://www.sota2.com/research/task/multi-hop>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.



## Benchmarks

Page 1 of 10. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/task/multi-hop.md?page=2>): Follow this link to discover more pages.

- [Multi-hop Question Answering on 2WikiMultiHopQA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa.md>): Multi-hop Question Answering; 2WikiMultiHopQA.

- [Multi-hop Question Answering on HotpotQA (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-test.md>): Multi-hop Question Answering; HotpotQA (test).

- [Multi-hop Question Answering on HotpotQA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-hop Question Answering on 2WikiMultiHopQA (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-test.md>): Multi-hop Question Answering; 2WikiMultiHopQA (test).

- [Multi-hop Question Answering on 2Wiki](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wiki.md>): Multi-hop Question Answering; 2Wiki.

- [Multi-hop Question Answering on Musique](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique.md>): Multi-hop Question Answering; Musique.

- [Multi-hop Question Answering on 2WikiMQA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimqa.md>): Multi-hop Question Answering; 2WikiMQA.

- [Multi-Hop Question Answering on HotpotQA (EM)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em.md>): Multi-Hop Question Answering; HotpotQA.

- [Multi-hop Question Answering on MuSiQue (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-test.md>): Multi-hop Question Answering; MuSiQue (test).

- [Multi-Hop QA on HotPotQA](<https://www.sota2.com/research/sota/multi-hop-qa-on-hotpotqa.md>): Multi-Hop QA; HotPotQA.

- [Exact Match Evaluation on Multi-Hop Question Answering on Bamboogle](<https://www.sota2.com/research/sota/exact-match-evaluation-on-multi-hop-question-answering-on-bamboogle.md>): Multi-Hop Question Answering; Bamboogle.

- [Multi-hop Question Answering on LoCoMo](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-locomo.md>): Multi-hop Question Answering; LoCoMo.

- [Multi-hop Question Answering on Bamboogle (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-test.md>): Multi-hop Question Answering; Bamboogle (test).

- [Multi-hop QA on MuSiQue](<https://www.sota2.com/research/sota/multi-hop-qa-on-musique.md>): Multi-hop QA; MuSiQue.

- [Multi-Hop Knowledge Graph Question Answering on WebQSP](<https://www.sota2.com/research/sota/multi-hop-knowledge-graph-question-answering-on-webqsp.md>): Multi-Hop Knowledge Graph Question Answering; WebQSP.

- [Multi-hop Question Answering on 2WikiMHQA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimhqa.md>): Multi-hop Question Answering; 2WikiMHQA.

- [Multi-Hop Knowledge Graph Question Answering on CWQ](<https://www.sota2.com/research/sota/multi-hop-knowledge-graph-question-answering-on-cwq.md>): Multi-Hop Knowledge Graph Question Answering; CWQ.

- [Multi-hop Question Answering on HotpotQA (EM, F1)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-hop Question Answering on Multi-hop RAG](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-multi-hop-rag.md>): Multi-hop Question Answering; Multi-hop RAG.

- [Multi-hop Question Answering on HotpotQA (EM, LLM Judge)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-llm-judge.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-hop Question Answering on 2WikiMultiHopQA Out-Of-Distribution (OOD)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-out-of-distribution-ood.md>): Multi-hop Question Answering; 2WikiMultiHopQA Out-Of-Distribution (OOD).

- [Multi-hop Question Answering on HotpotQA (dev)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-dev.md>): Multi-hop Question Answering; HotpotQA (dev).

- [Multi-hop Question Answering on 2WikiQA (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikiqa-test.md>): Multi-hop Question Answering; 2WikiQA (test).

- [Multi-Hop Reasoning on LoCoMo](<https://www.sota2.com/research/sota/multi-hop-reasoning-on-locomo.md>): Multi-Hop Reasoning; LoCoMo.

- [Multi-Hop Knowledge Graph Question Answering on GrailQA](<https://www.sota2.com/research/sota/multi-hop-knowledge-graph-question-answering-on-grailqa.md>): Multi-Hop Knowledge Graph Question Answering; GrailQA.

- [Multi-hop QA on 2WikiMultihopQA](<https://www.sota2.com/research/sota/multi-hop-qa-on-2wikimultihopqa.md>): Multi-hop QA; 2WikiMultihopQA.

- [Multi-Hop Question Answering on HotpotQA (EM, F1, SD, SE)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-sd-se.md>): Multi-Hop Question Answering; HotpotQA.

- [Multi-Hop Question Answering on HotpotQA, 2Wiki, Musique, and Bamboogle (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-2wiki-musique-and-bamboogle-test.md>): Multi-Hop Question Answering; Multi-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle) (test).

- [Multi-Hop Question Answering on HotpotQA, 2Wiki, Musique, and Bamboogle](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-2wiki-musique-and-bamboogle.md>): Multi-Hop Question Answering; Multi-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle).

- [Multi-hop Question Answering on HotpotQA fullwiki setting (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-fullwiki-setting-test.md>): Multi-hop Question Answering; HotpotQA fullwiki setting (test).

- [Multi-hop Question Answering on Bamboogle](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle.md>): Multi-hop Question Answering; Bamboogle.

- [Multi-hop tool use on ToolHop](<https://www.sota2.com/research/sota/multi-hop-tool-use-on-toolhop.md>): Multi-hop tool use; ToolHop.

- [Multi-Hop Question Answering on MuSiQue (EM)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em.md>): Multi-Hop Question Answering; MuSiQue.

- [Multi-Hop Question Answering on Bamboogle (EM, F1, SD, SE)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-em-f1-sd-se.md>): Multi-Hop Question Answering; Bamboogle.

- [Multi-hop Question Answering on HotPotQA (Task Success, CoT, Latency)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-task-success-cot-latency.md>): Multi-hop Question Answering; HotPotQA.

- [Multi-Hop Question Answering on HotpotQA (SubEM, F1)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-subem-f1.md>): Multi-Hop Question Answering; HotpotQA.

- [Multi-Hop Question Answering on HotpotQA in-domain](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-in-domain.md>): Multi-Hop Question Answering; HotpotQA in-domain.

- [Multi-Hop Question Answering on MuSiQue (Exact Match (EM))](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-exact-match-em.md>): Multi-Hop Question Answering; MuSiQue.

- [Multi-Hop Question Answering on Bamboogle (EM, F1)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-em-f1.md>): Multi-Hop Question Answering; Bamboogle.

- [Multi-hop Question Answering on Average (MuSiQue, HotpotQA, 2WikiMultiHopQA, LongSeal)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-average-musique-hotpotqa-2wikimultihopqa-longseal.md>): Multi-hop Question Answering; Average (MuSiQue, HotpotQA, 2WikiMultiHopQA, LongSeal).

- [Multi-hop Question Answering on LongSeal](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-longseal.md>): Multi-hop Question Answering; LongSeal.

- [Multi-hop Question Answering on HotpotQA (EM, F1, Rate)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-rate.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-hop Question Answering on MuSiQue (EM, F1, Rate)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em-f1-rate.md>): Multi-hop Question Answering; MuSiQue.

- [Multi-Hop Question Answering on Bamboogle (test) (Exact Match (EM))](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-test-exact-match-em.md>): Multi-Hop Question Answering; Bamboogle (test).

- [Multi-hop Question Answering on MusiQue (EM, F1, EFR)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em-f1-efr.md>): Multi-hop Question Answering; MusiQue.

- [Multi-hop Reasoning on StrategyQA](<https://www.sota2.com/research/sota/multi-hop-reasoning-on-strategyqa.md>): Multi-hop Reasoning; StrategyQA.

- [Multi-hop Reasoning on MuSiQue (Accuracy)](<https://www.sota2.com/research/sota/multi-hop-reasoning-on-musique-accuracy.md>): Multi-hop Reasoning; MuSiQue.

- [Multi-hop Question Answering on HotpotQA (EM, F1, Faithfulness)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-faithfulness.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-Hop QA on Bamboogle (Exact Match (EM))](<https://www.sota2.com/research/sota/multi-hop-qa-on-bamboogle-exact-match-em.md>): Multi-Hop QA; Bamboogle.

- [Multi-hop Question Answering on FRAMES (Accuracy)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-frames-accuracy.md>): Multi-hop Question Answering; FRAMES.

- [Multi-hop Multiple-choice Question Answering on T2S-Bench-MR 1.0 (test)](<https://www.sota2.com/research/sota/multi-hop-multiple-choice-question-answering-on-t2s-bench-mr-1-0-test.md>): Multi-hop Multiple-choice Question Answering; T2S-Bench-MR 1.0 (test).

- [Multi-hop Question Answering on MuSiQue (Str-Acc, LLM-Acc)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-str-acc-llm-acc.md>): Multi-hop Question Answering; MuSiQue.

- [Multi-hop Question Answering on 2WikiMultiHopQA (Str-Acc, LLM-Acc)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-str-acc-llm-acc.md>): Multi-hop Question Answering; 2WikiMultiHopQA.

- [Multi-Hop Question Answering on Bamboogle (Accuracy)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-accuracy.md>): Multi-Hop Question Answering; Bamboogle.

- [Multi-Hop Question Answering on 2Wiki (Accuracy)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wiki-accuracy.md>): Multi-Hop Question Answering; 2Wiki.

- [Multi-hop Question Answering on 2WikiMultiHopQA (val)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-val.md>): Multi-hop Question Answering; 2WikiMultiHopQA (val).

- [Multi-hop Retrieval on HotpotQA](<https://www.sota2.com/research/sota/multi-hop-retrieval-on-hotpotqa.md>): Multi-hop Retrieval; HotpotQA.

- [Multi-hop QA on 2Wiki](<https://www.sota2.com/research/sota/multi-hop-qa-on-2wiki.md>): Multi-hop QA; 2Wiki.

- [Multi-hop QA Retrieval on MuSiQue (test)](<https://www.sota2.com/research/sota/multi-hop-qa-retrieval-on-musique-test.md>): Multi-hop QA Retrieval; MuSiQue (test).

- [Multi-hop Reasoning on MuSiQue](<https://www.sota2.com/research/sota/multi-hop-reasoning-on-musique.md>): Multi-hop Reasoning; MuSiQue.

- [Multi-hop Question Answering on MuSiQue (EM, F1, Acc)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em-f1-acc.md>): Multi-hop Question Answering; MuSiQue.

- [Multi-hop Question Answering on HotpotQA fullwiki setting (dev)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-fullwiki-setting-dev.md>): Multi-hop Question Answering; HotpotQA fullwiki setting (dev).

- [Multi-hop Question Answering on Multi-Hop QA (Aggregated)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-multi-hop-qa-aggregated.md>): Multi-hop Question Answering; Multi-Hop QA.

- [Multi-hop Question Answering on WebQSP](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-webqsp.md>): Multi-hop Question Answering; WebQSP.

- [Multi-hop Question Answering on Mintaka](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-mintaka.md>): Multi-hop Question Answering; Mintaka.

- [Multi-hop Question Answering on SimpleQA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-simpleqa.md>): Multi-hop Question Answering; SimpleQA.

- [Multi-hop Question Answering on ExaQT](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-exaqt.md>): Multi-hop Question Answering; ExaQT.

- [Multi-hop Question Answering on CWQ](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-cwq.md>): Multi-hop Question Answering; CWQ.

- [Multi-hop Question Answering on MuSiQue (F1, ROUGHL, EM)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-f1-roughl-em.md>): Multi-hop Question Answering; MuSiQue.

- [Multi-hop Question Answering on MuSiQue (test) (Cost and Repair Metrics)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-test-cost-and-repair-metrics.md>): Multi-hop Question Answering; MuSiQue (test).

- [Multi-hop QA Retrieval on MuSiQue](<https://www.sota2.com/research/sota/multi-hop-qa-retrieval-on-musique.md>): Multi-hop QA Retrieval; MuSiQue.

- [Biomedical Multi-hop Question Answering on CondMedQA](<https://www.sota2.com/research/sota/biomedical-multi-hop-question-answering-on-condmedqa.md>): Biomedical Multi-hop Question Answering; CondMedQA.

- [Multi-hop Question Answering on 2WikiMultiHopQA (dev)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-dev.md>): Multi-hop Question Answering; 2WikiMultiHopQA (dev).

- [Multi-Hop Question Answering on Multi-Hop QA](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-multi-hop-qa.md>): Multi-Hop Question Answering; Multi-Hop QA.

- [Multi-hop Question Answering on HotpotQA fullwiki (val)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-fullwiki-val.md>): Multi-hop Question Answering; HotpotQA fullwiki (val).

- [Multi-hop Question Answering on 2Wiki (test)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wiki-test.md>): Multi-hop Question Answering; 2Wiki (test).

- [Multi-hop QA Retrieval on 2WikiMultihopQA (test)](<https://www.sota2.com/research/sota/multi-hop-qa-retrieval-on-2wikimultihopqa-test.md>): Multi-hop QA Retrieval; 2WikiMultihopQA (test).

- [Multi-hop Question Answering on HotpotQA (Performance Score)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-performance-score.md>): Multi-hop Question Answering; HotpotQA.

- [Multi-hop QA Retrieval on 2Wiki](<https://www.sota2.com/research/sota/multi-hop-qa-retrieval-on-2wiki.md>): Multi-hop QA Retrieval; 2Wiki.

- [Multi-hop Question Answering on HotpotQA (Avg@8 accuracy)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-avg-at-8-accuracy.md>): Multi-hop Question Answering; HotpotQA.
