| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HotpotQA | G-reasoner | Recall@285.9 | 44 | 21d ago | |
| MultiHop-RAG (test) | ScalDPP | NDCG@1063.26 | 24 | 1mo ago | |
| Average (HotpotQA, 2WikiMultihopQA, Musique, Morehopqa) (test) | ThinkGR | Average Recall78.44 | 16 | 12d ago | |
| Morehopqa (test) | ThinkGR | Recall80.5 | 16 | 12d ago | |
| HotPotQA | Search-R1-7B | Latency (s)0.065 | 15 | 12d ago | |
| Average (MuSiQue, 2Wiki, HotpotQA) | GFM-RAG | R@272.5 | 10 | 2mo ago | |
| Musique | MDR | Latency (s/query)0.05 | 9 | 12d ago | |
| 2WikiMultihopQA | MDR | Latency (s/query)0.06 | 9 | 12d ago | |
| Multi-hop 4 datasets aggregate (test) | Ours | NDCG@1058.5 | 8 | 3mo ago | |
| STaRK-Prime multi-hop (test) | GIN | Hits@134.1 | 6 | 12d ago | |
| HotpotQA Fullwiki (test) | MDR | Retrieval EM85.6 | 4 | 3mo ago | |
| MuSiQue (val) | AAR | R@548.8 | 3 | 1mo ago | |
| MuSiQue | CARE | Accuracy75.5 | 3 | 1mo ago | |
| HotPotQA | CARE | Accuracy82.7 | 3 | 1mo ago | |
| 2Wiki (test) | PHASEGRAPH | LASTOP@553.6 | 3 | 2mo ago | |
| MuSiQue (test) | LASTHOP@576.8 | 3 | 2mo ago |