# Open-Domain Question Answering on NaturalQuestions (NQ) v1.0 (test)

Source: [Open-Domain Question Answering on NaturalQuestions (NQ) v1.0 (test)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-naturalquestions-nq-v1-0-test>)

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

Data updated: 2026-02-26T05:26:57.371Z

Evaluation of model performance on the test split (v1.0) of the Natural Questions (NQ) dataset for Open-Domain Question Answering, measured using Top-K Accuracy (Acc@20, Acc@100).

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 | Open-Domain Question Answering |
| Dataset (including any stated split) | NaturalQuestions (NQ) v1.0 (test) |
| Metric | Acc@20 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Acc@20](<https://www.sota2.com/research/sota/open-domain-question-answering-on-naturalquestions-nq-v1-0-test.md?metric=Acc%4020>): Higher is better; unit: PERCENT.

- [Acc@100](<https://www.sota2.com/research/sota/open-domain-question-answering-on-naturalquestions-nq-v1-0-test.md?metric=Acc%40100>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc@20 | Result date | Report paper |
| --- | --- | --- | --- |
| SPAR-Wiki | 83 | Not recorded | 68fa6de91e209131cea3cdff |
| RocketQA | 82.7 | Not recorded | 68fa6de91e209131cea3cdff |
| SPAR-PAQ | 82.7 | Not recorded | 68fa6de91e209131cea3cdff |
| DPR + BM25 | 82.6 | Not recorded | 68fa6de91e209131cea3cdff |
| xMoCo | 82.5 | Not recorded | 68fa6de91e209131cea3cdff |
| SPAR-MARCO | 82.3 | Not recorded | 68fa6de91e209131cea3cdff |
| ANCE | 82.1 | Not recorded | 68fa6de91e209131cea3cdff |
| DPR multi | 79.5 | Not recorded | 68fa6de91e209131cea3cdff |
| PAQ A | 63.8 | Not recorded | 68fa6de91e209131cea3cdff |
| BM25 | 62.9 | Not recorded | 68fa6de91e209131cea3cdff |
| Wiki A | 62 | Not recorded | 68fa6de91e209131cea3cdff |

### SPAR-Wiki

Acc@20: 83. Result ID: 698ffabb3a6c314849fd3783.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Implementation](<https://github.com/facebookresearch/dpr-scale/tree/main/spar>)

Recorded evaluation configuration: {"Model Type":"dense","Teacher":"BM25","Base Model":"Wiki"}. This record does not assert independent reproduction.

### RocketQA

Acc@20: 82.7. Result ID: 698ffabb3a6c314849fd3781.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f31e209131cea25300.md>)

[Implementation](<https://github.com/PaddlePaddle/Research/tree/master/NLP/NAACL2021-RocketQA>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

### SPAR-PAQ

Acc@20: 82.7. Result ID: 698ffabb3a6c314849fd3784.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Implementation](<https://github.com/facebookresearch/dpr-scale/tree/main/spar>)

Recorded evaluation configuration: {"Model Type":"dense","Teacher":"BM25","Base Model":"PAQ"}. This record does not assert independent reproduction.

### DPR + BM25

Acc@20: 82.6. Result ID: 698ffabb3a6c314849fd3782.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

Recorded evaluation configuration: {"Model Type":"hybrid"}. This record does not assert independent reproduction.

### xMoCo

Acc@20: 82.5. Result ID: 698ffabb3a6c314849fd377f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

### SPAR-MARCO

Acc@20: 82.3. Result ID: 698ffabb3a6c314849fd3785.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Implementation](<https://github.com/facebookresearch/dpr-scale/tree/main/spar>)

Recorded evaluation configuration: {"Model Type":"dense","Evaluation Mode":"Cross-dataset model generalization"}. This record does not assert independent reproduction.

### ANCE

Acc@20: 82.1. Result ID: 698ffabb3a6c314849fd3780.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68881e209131cea1cb62.md>)

[Implementation](<https://aka.ms/ance>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

### DPR multi

Acc@20: 79.5. Result ID: 698ffabb3a6c314849fd377e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c190.md>)

[Implementation](<https://github.com/facebookresearch/DPR>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

### PAQ A

Acc@20: 63.8. Result ID: 698ffabb3a6c314849fd377d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

### BM25

Acc@20: 62.9. Result ID: 698ffabb3a6c314849fd377b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

Recorded evaluation configuration: {"Model Type":"sparse"}. This record does not assert independent reproduction.

### Wiki A

Acc@20: 62. Result ID: 698ffabb3a6c314849fd377c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de91e209131cea3cdff.md>)

Recorded evaluation configuration: {"Model Type":"dense"}. This record does not assert independent reproduction.

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