# Passage Reranking on ArguAna BEIR Source: [Passage Reranking on ArguAna BEIR]() Collection index: [llms.txt]() Data updated: 2026-04-21T09:59:20.374Z Evaluation of Passage Reranking performance on the ArguAna dataset, a specific component within the BEIR benchmark suite. 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. | Scope | Recorded value | | --- | --- | | Task | Passage Reranking | | Dataset (including any stated split) | ArguAna BEIR | | Metric | NDCG@10 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [NDCG@10](): Higher is better; unit: PERCENT. - [SR](): Higher is better; unit: PERCENT. ## Recorded results | Method | NDCG@10 | Result date | Report paper | | --- | --- | --- | --- | | HeadRank | 36.59 | Not recorded | 69e704cc7d0172140ec7efac | | HeadRank | 35.3 | Not recorded | 69e704cc7d0172140ec7efac | | HeadRank | 34.62 | Not recorded | 69e704cc7d0172140ec7efac | | CoRe | 34.59 | Not recorded | 69e704cc7d0172140ec7efac | | QR-R | 34.39 | Not recorded | 69e704cc7d0172140ec7efac | | NIAH | 33.87 | Not recorded | 69e704cc7d0172140ec7efac | | CoRe | 33.61 | Not recorded | 69e704cc7d0172140ec7efac | | QR-R | 33.52 | Not recorded | 69e704cc7d0172140ec7efac | | NIAH | 33 | Not recorded | 69e704cc7d0172140ec7efac | | CoRe | 32.93 | Not recorded | 69e704cc7d0172140ec7efac | | ICR | 32.43 | Not recorded | 69e704cc7d0172140ec7efac | | QR-R | 32.35 | Not recorded | 69e704cc7d0172140ec7efac | | ICR | 30.63 | Not recorded | 69e704cc7d0172140ec7efac | | BM25 (top40) | 29.99 | Not recorded | 69e704cc7d0172140ec7efac | | RankGPT | 27.72 | Not recorded | 69e704cc7d0172140ec7efac | | RankGPT | 27.47 | Not recorded | 69e704cc7d0172140ec7efac | | RankGPT | 26.44 | Not recorded | 69e704cc7d0172140ec7efac | | NIAH | 24.91 | Not recorded | 69e704cc7d0172140ec7efac | | ICR | 23.68 | Not recorded | 69e704cc7d0172140ec7efac | ### HeadRank NDCG@10: 36.59. Result ID: 69e74a6947f34ce924ce068d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### HeadRank NDCG@10: 35.3. Result ID: 69e74a6947f34ce924ce0693. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### HeadRank NDCG@10: 34.62. Result ID: 69e74a6947f34ce924ce0687. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### CoRe NDCG@10: 34.59. Result ID: 69e74a6947f34ce924ce068a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### QR-R NDCG@10: 34.39. Result ID: 69e74a6947f34ce924ce0685. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### NIAH NDCG@10: 33.87. Result ID: 69e74a6947f34ce924ce0686. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### CoRe NDCG@10: 33.61. Result ID: 69e74a6947f34ce924ce0684. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### QR-R NDCG@10: 33.52. Result ID: 69e74a6947f34ce924ce068b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### NIAH NDCG@10: 33. Result ID: 69e74a6947f34ce924ce068c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### CoRe NDCG@10: 32.93. Result ID: 69e74a6947f34ce924ce0690. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### ICR NDCG@10: 32.43. Result ID: 69e74a6947f34ce924ce0683. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### QR-R NDCG@10: 32.35. Result ID: 69e74a6947f34ce924ce0691. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### ICR NDCG@10: 30.63. Result ID: 69e74a6947f34ce924ce0689. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### BM25 (top40) NDCG@10: 29.99. Result ID: 69e74a6947f34ce924ce0681. [Reporting paper]() Recorded evaluation configuration: {"Model":"Baseline","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### RankGPT NDCG@10: 27.72. Result ID: 69e74a6947f34ce924ce068e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### RankGPT NDCG@10: 27.47. Result ID: 69e74a6947f34ce924ce0688. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### RankGPT NDCG@10: 26.44. Result ID: 69e74a6947f34ce924ce0682. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-0.6B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### NIAH NDCG@10: 24.91. Result ID: 69e74a6947f34ce924ce0692. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. ### ICR NDCG@10: 23.68. Result ID: 69e74a6947f34ce924ce068f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Top-40 retrieval setting":"BM25"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.