Retrieval on DetectiveQA
32.22Recall@3QRRanker-4B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| QRRanker-4Bmethod_category=Reranking Methods, rerank_top_k=50, initial_retriever=SFT-Embedding-8B, evaluation_details=averaged over English and Chinese sets2026.02 | 32.22 | 41.32 | 53.76 | |
| Qwen-Reranker-4B (trained)method_category=Reranking Methods, rerank_top_k=50, initial_retriever=SFT-Embedding-8B, status=trained, evaluation_details=averaged over English and Chinese sets2026.02 | 29.67 | 38.92 | 51.25 | |
| GroupRank-32B*method_category=Reranking Methods, rerank_top_k=50, initial_retriever=SFT-Embedding-8B, run_type=single run evaluation, evaluation_details=averaged over English and Chinese sets2026.02 | 29.34 | 39.21 | 51.38 | |
| QRHeads-4B (out-of-box)method_category=Reranking Methods, rerank_top_k=50, initial_retriever=SFT-Embedding-8B, status=out-of-box, evaluation_details=averaged over English and Chinese sets2026.02 | 23.71 | 32.89 | 45.58 | |
| Qwen-Reranker-4B (out-of-box)method_category=Reranking Methods, rerank_top_k=50, initial_retriever=SFT-Embedding-8B, status=out-of-box, evaluation_details=averaged over English and Chinese sets2026.02 | 23.42 | 30.5 | 42.09 | |
| SFT-Embedding-8Bmethod_category=Embedding Methods, evaluation_details=averaged over English and Chinese sets2026.02 | 19.84 | 27.59 | 39 | |
| Qwen3-Embedding-4Bmethod_category=Embedding Methods, evaluation_details=averaged over English and Chinese sets2026.02 | 19.25 | 26.17 | 37.04 | |
| Qwen3-Embedding-8Bmethod_category=Embedding Methods, evaluation_details=averaged over English and Chinese sets2026.02 | 12.84 | 20 | 31.17 |