# Open-Domain Question Answering Retrieval on EntityQuestions (test)

Source: [Open-Domain Question Answering Retrieval on EntityQuestions (test)](<https://www.sota2.com/research/sota/open-domain-question-answering-retrieval-on-entityquestions-test>)

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

Data updated: 2026-02-26T05:34:38.484Z

Evaluation of Open-Domain Question Answering Retrieval performance on the test split of the EntityQuestions dataset, reporting Accuracy at top 20 and top 100 retrieval ranks.

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 Retrieval |
| Dataset (including any stated split) | EntityQuestions (test) |
| Metric | Accuracy@20 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

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

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

## Recorded results

| Method | Accuracy@20 | Result date | Report paper |
| --- | --- | --- | --- |
| COS | 76.3 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| SPAR-PAQ | 74 | Not recorded | 68fa6de91e209131cea3cdff |
| SPAR | 73.6 | Not recorded | 68fa6de91e209131cea3cdff |
| SPAR-wiki | 73.6 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| DPR + BM25 | 73.3 | Not recorded | 68fa6de91e209131cea3cdff |
| BM25 | 70.8 | Not recorded | 68fa6de91e209131cea3cdff |
| BM25 | 70.8 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| BM25 | 70.8 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| COS (pretrain-only) | 70.7 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| PAQ Λ | 69.4 | Not recorded | 68fa6de91e209131cea3cdff |
| Wiki Λ | 68.4 | Not recorded | 68fa6de91e209131cea3cdff |
| Spider | 65.1 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| Contriever | 61.8 | Not recorded | 68fa6f7f1e209131cea45fd0 |
| DPR | 56.6 | Not recorded | 68fa6de91e209131cea3cdff |
| DPR-multi | 56.6 | Not recorded | 68fa6f7f1e209131cea45fd0 |

### COS

Accuracy@20: 76.3. Result ID: 6990c62b3a6c314849032c82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Implementation](<https://github.com/Mayer123/UDT-QA>)

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

### SPAR-PAQ

Accuracy@20: 74. Result ID: 698ffabb3a6c314849fd37a8.

[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: {"type":"dense","zero-shot":"true","averaging":"micro-average"}. This record does not assert independent reproduction.

### SPAR

Accuracy@20: 73.6. Result ID: 698ffabb3a6c314849fd37a7.

[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: {"type":"dense","zero-shot":"true","averaging":"micro-average"}. This record does not assert independent reproduction.

### SPAR-wiki

Accuracy@20: 73.6. Result ID: 6990c62b3a6c314849032c81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.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: Not recorded. This record does not assert independent reproduction.

### DPR + BM25

Accuracy@20: 73.3. Result ID: 698ffabb3a6c314849fd37a4.

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

Recorded evaluation configuration: {"type":"hybrid","zero-shot":"true","averaging":"micro-average"}. This record does not assert independent reproduction.

### BM25

Accuracy@20: 70.8. Result ID: 698ffabb3a6c314849fd37a3.

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

Recorded evaluation configuration: {"type":"sparse","zero-shot":"true","averaging":"micro-average"}. This record does not assert independent reproduction.

### BM25

Accuracy@20: 70.8. Result ID: 6990c62b3a6c314849032c7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

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

### BM25

Accuracy@20: 70.8. Result ID: 6990c62b3a6c314849032cc5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

Recorded evaluation configuration: {"Zero-shot":true}. This record does not assert independent reproduction.

### COS (pretrain-only)

Accuracy@20: 70.7. Result ID: 6990c62b3a6c314849032cc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Implementation](<https://github.com/Mayer123/UDT-QA>)

Recorded evaluation configuration: {"Zero-shot":true}. This record does not assert independent reproduction.

### PAQ Λ

Accuracy@20: 69.4. Result ID: 698ffabb3a6c314849fd37a6.

[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: {"type":"dense","zero-shot":"true","averaging":"micro-average","training\_source":"PAQ"}. This record does not assert independent reproduction.

### Wiki Λ

Accuracy@20: 68.4. Result ID: 698ffabb3a6c314849fd37a5.

[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: {"type":"dense","zero-shot":"true","averaging":"micro-average","training\_source":"Wikipedia"}. This record does not assert independent reproduction.

### Spider

Accuracy@20: 65.1. Result ID: 6990c62b3a6c314849032cc7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34f32.md>)

Recorded evaluation configuration: {"Zero-shot":true}. This record does not assert independent reproduction.

### Contriever

Accuracy@20: 61.8. Result ID: 6990c62b3a6c314849032cc6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4b1e209131cea38d50.md>)

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

Recorded evaluation configuration: {"Zero-shot":true}. This record does not assert independent reproduction.

### DPR

Accuracy@20: 56.6. Result ID: 698ffabb3a6c314849fd37a2.

[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: {"type":"dense","zero-shot":"true","averaging":"micro-average"}. This record does not assert independent reproduction.

### DPR-multi

Accuracy@20: 56.6. Result ID: 6990c62b3a6c314849032c80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fd0.md>)

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

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

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.
