# Information Retrieval on BEIR (NQ, HotpotQA, SciFact subset)

Source: [Information Retrieval on BEIR (NQ, HotpotQA, SciFact subset)](<https://www.sota2.com/research/sota/information-retrieval-on-beir-nq-hotpotqa-scifact-subset>)

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

Data updated: 2026-05-06T09:06:11.702Z

Evaluation of Information Retrieval performance across a mixed workload subset of the BEIR benchmark suite, specifically including NQ, HotpotQA, and SciFact datasets, measured using Recall@10, MRR@10, and nDCG@10.

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 | Information Retrieval |
| Dataset (including any stated split) | BeIR nq, hotpotqa, scifact (mixed workload) |
| Metric | Recall@10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Recall@10](<https://www.sota2.com/research/sota/information-retrieval-on-beir-nq-hotpotqa-scifact-subset.md?metric=Recall%4010>): Higher is better; unit: PERCENT.

- [MRR@10](<https://www.sota2.com/research/sota/information-retrieval-on-beir-nq-hotpotqa-scifact-subset.md?metric=MRR%4010>): Higher is better; unit: PERCENT.

- [nDCG@10](<https://www.sota2.com/research/sota/information-retrieval-on-beir-nq-hotpotqa-scifact-subset.md?metric=nDCG%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall@10 | Result date | Report paper |
| --- | --- | --- | --- |
| Hybrid RRF | 94.28 | Not recorded | 69facb4cc0f56ed84308a641 |
| Experience-RAG Skill | 94.28 | Not recorded | 69facb4cc0f56ed84308a641 |
| Dense | 91.36 | Not recorded | 69facb4cc0f56ed84308a641 |
| BM25 | 90.12 | Not recorded | 69facb4cc0f56ed84308a641 |
| Rewrite-BM25 | 89.56 | Not recorded | 69facb4cc0f56ed84308a641 |

### Hybrid RRF

Recall@10: 94.28. Result ID: 69fb047f47f34ce924de2049.

[Reporting paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Experience-RAG Skill

Recall@10: 94.28. Result ID: 69fb047f47f34ce924de204a.

[Reporting paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Dense

Recall@10: 91.36. Result ID: 69fb047f47f34ce924de2048.

[Reporting paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BM25

Recall@10: 90.12. Result ID: 69fb047f47f34ce924de2046.

[Reporting paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Rewrite-BM25

Recall@10: 89.56. Result ID: 69fb047f47f34ce924de2047.

[Reporting paper](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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