# Open-domain Question Answering on Natural Questions (scarce)

Source: [Open-domain Question Answering on Natural Questions (scarce)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-natural-questions-scarce>)

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

Data updated: 2026-02-26T05:41:42.364Z

Evaluation of model performance on the scarce subset of the Natural Questions dataset for Open-domain Question Answering, measured using Exact Match and F1 scores.

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) | Natural Questions (scarce) |
| Metric | EM & F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [EM & F1 Score](<https://www.sota2.com/research/sota/open-domain-question-answering-on-natural-questions-scarce.md?metric=EM%20%26%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM & F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Thrust | 35.9 | Not recorded | 68fa777a1e209131cea73718 |
| Thrust | 34.8 | Not recorded | 68fa777a1e209131cea73718 |
| Thrust | 33 | Not recorded | 68fa777a1e209131cea73718 |
| Default | 20 | Not recorded | 68fa777a1e209131cea73718 |
| Default | 12.8 | Not recorded | 68fa777a1e209131cea73718 |
| Default | 12 | Not recorded | 68fa777a1e209131cea73718 |

### Thrust

EM & F1 Score: 35.9. Result ID: 6995385a3badfaffe61f0509.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-3b"}. This record does not assert independent reproduction.

### Thrust

EM & F1 Score: 34.8. Result ID: 6995385a3badfaffe61f0507.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-large"}. This record does not assert independent reproduction.

### Thrust

EM & F1 Score: 33. Result ID: 6995385a3badfaffe61f0505.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-base"}. This record does not assert independent reproduction.

### Default

EM & F1 Score: 20. Result ID: 6995385a3badfaffe61f0504.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-base"}. This record does not assert independent reproduction.

### Default

EM & F1 Score: 12.8. Result ID: 6995385a3badfaffe61f0508.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-3b"}. This record does not assert independent reproduction.

### Default

EM & F1 Score: 12. Result ID: 6995385a3badfaffe61f0506.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73718.md>)

Recorded evaluation configuration: {"Backbone":"UnifiedQA-large"}. This record does not assert independent reproduction.

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