Retrieval on BRIGHT v1 (leaderboard)
46.8Average Retrieval ScoreDIVER(v3)
Evaluation results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DIVER(v3)Retriever=BGE-Reasoner-Embed-0928, Reranker=Groupwise reranking2025.08 | 46.8 | 66 | 63.7 | 42.4 | 55 | 40.6 | 44.7 | 50.4 | 32.5 | 47.3 | 17.2 | 46.4 | 55.6 | |
| DIVER(v2)Expansion=Advanced query expansion, Reranker=Combined pointwise and listwise DIVER-Rerank2025.08 | 45.8 | 68 | 62.5 | 42 | 58.2 | 41.5 | 44.3 | 49.2 | 34.8 | 32.9 | 19.1 | 44.3 | 52.6 | |
| BGE-Reasoner2025.08 | 45.2 | 66.5 | 63.7 | 39.4 | 50.3 | 37 | 42.9 | 43.7 | 35.1 | 44.3 | 17.2 | 44.2 | 58.5 | |
| DIVER(v1)components=DIVER-QExpand, DIVER-Retriever, and DIVER-Rerank-Pointwise2025.08 | 41.6 | 62.2 | 58.7 | 34.4 | 52.9 | 35.6 | 36.5 | 42.9 | 38.9 | 25.4 | 18.3 | 40 | 53.1 | |
| ReasonRank2025.08 | 40.8 | 62.7 | 55.5 | 36.7 | 54.6 | 35.7 | 38 | 44.8 | 29.5 | 25.6 | 14.4 | 42 | 50.1 | |
| XRR22025.08 | 40.3 | 63.1 | 55.4 | 38.5 | 52.9 | 37.1 | 38.2 | 44.6 | 21.9 | 35 | 15.7 | 34.4 | 46.2 | |
| RaDeR with QwenRerankMethod=RaDeR, Reranker=QwenRerank2025.08 | 39.2 | 58 | 59.2 | 33 | 49.4 | 31.8 | 39 | 36.4 | 33.5 | 33.3 | 10.8 | 34.2 | 51.6 | |
| ReasonIR with Rank-R1-32BMethod=ReasonIR, Reranker=Rank-R1-32B2025.08 | 38.8 | 59.5 | 55.1 | 37.9 | 52.7 | 30 | 39.3 | 45.1 | 32.1 | 17.1 | 10.7 | 40.4 | 45.6 | |
| ReasonIR with QwenRerankMethod=ReasonIR, Reranker=QwenRerank2025.08 | 36.9 | 58.2 | 53.2 | 32 | 43.6 | 28.8 | 37.6 | 36 | 33.2 | 34.8 | 7.9 | 32.6 | 45 | |
| GPT4 with Rank1-32BBackbone=GPT4, Reranker=Rank1-32B2025.08 | 29.4 | 49.7 | 35.8 | 22 | 37.5 | 22.5 | 21.7 | 35 | 18.8 | 32.5 | 10.8 | 22.9 | 43.7 | |
| Qwen1.5-7B with InteRank-3BBackbone=Qwen1.5-7B, Reranker=InteRank-3B2025.08 | 27.4 | 51.2 | 51.4 | 22.4 | 31.9 | 17.3 | 26.6 | 22.4 | 24.5 | 23.1 | 13.5 | 19.3 | 25.5 | |
| Rank-R1-14B2025.08 | 20.5 | 31.2 | 38.5 | 21.2 | 26.4 | 22.6 | 18.9 | 27.5 | 9.2 | 20.2 | 9.7 | 11.9 | 9.2 |