# Single-hop Question Answering on Natural Questions (NQ) (test)

Source: [Single-hop Question Answering on Natural Questions (NQ) (test)](<https://www.sota2.com/research/sota/single-hop-question-answering-on-natural-questions-nq-test>)

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

Data updated: 2026-03-05T06:56:53.089Z

Evaluation of model performance on the test split of the Natural Questions (NQ) dataset specifically for single-hop question answering, measured using EM 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 | Single-hop Question Answering |
| Dataset (including any stated split) | Natural Questions (NQ) (test) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 33 of 33 |
| 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](<https://www.sota2.com/research/sota/single-hop-question-answering-on-natural-questions-nq-test.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/single-hop-question-answering-on-natural-questions-nq-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| SE-Search-3B | 47.5 | Not recorded | 69a90ddc2d603e6de3e40587 |
| AutoRefine-Base | 46.7 | Not recorded | 69a90ddc2d603e6de3e40587 |
| O2-Searcher | 44.4 | Not recorded | 69a90ddc2d603e6de3e40587 |
| AutoRefine-Instruct | 43.6 | Not recorded | 69a90ddc2d603e6de3e40587 |
| ZeroSearch-Base | 43 | Not recorded | 69a90ddc2d603e6de3e40587 |
| ReSearch-Base | 42.7 | Not recorded | 69a90ddc2d603e6de3e40587 |
| Search-R1-Base | 42.1 | Not recorded | 69a90ddc2d603e6de3e40587 |
| InForage | 42.1 | Not recorded | 69a90ddc2d603e6de3e40587 |
| Search-R1-Instruct | 39.7 | Not recorded | 69a90ddc2d603e6de3e40587 |
| ReSearch-Instruct | 36.5 | Not recorded | 69a90ddc2d603e6de3e40587 |
| ProGraph-R1 | 35.94 | Not recorded | 69784684a2b28e761d87c4dc |
| Naive RAG | 34.8 | Not recorded | 69a90ddc2d603e6de3e40587 |
| ProGraph-R1 | 34.38 | Not recorded | 69784684a2b28e761d87c4dc |
| Graph-R1 | 33.59 | Not recorded | 69784684a2b28e761d87c4dc |
| Search-R1 | 32.03 | Not recorded | 69784684a2b28e761d87c4dc |
| R1-Searcher | 32.03 | Not recorded | 69784684a2b28e761d87c4dc |
| Graph-R1 | 30.47 | Not recorded | 69784684a2b28e761d87c4dc |
| SFT | 24.9 | Not recorded | 69a90ddc2d603e6de3e40587 |
| Search-R1 | 24.22 | Not recorded | 69784684a2b28e761d87c4dc |
| R1-Searcher | 24.22 | Not recorded | 69784684a2b28e761d87c4dc |
| Search-o1 | 23.8 | Not recorded | 69a90ddc2d603e6de3e40587 |
| R1-Base | 22.6 | Not recorded | 69a90ddc2d603e6de3e40587 |
| R1-Instruct | 21 | Not recorded | 69a90ddc2d603e6de3e40587 |
| R1 | 16.41 | Not recorded | 69784684a2b28e761d87c4dc |
| R1 | 11.72 | Not recorded | 69784684a2b28e761d87c4dc |
| IRCoT | 11.1 | Not recorded | 69a90ddc2d603e6de3e40587 |
| Direct Generation | 10.6 | Not recorded | 69a90ddc2d603e6de3e40587 |
| SFT | 5.12 | Not recorded | 69784684a2b28e761d87c4dc |
| SFT | 3.12 | Not recorded | 69784684a2b28e761d87c4dc |
| NaiveGeneration | 2.34 | Not recorded | 69784684a2b28e761d87c4dc |
| NaiveGeneration | 1.56 | Not recorded | 69784684a2b28e761d87c4dc |
| StandardRAG | 1.56 | Not recorded | 69784684a2b28e761d87c4dc |
| StandardRAG | 0 | Not recorded | 69784684a2b28e761d87c4dc |

### SE-Search-3B

EM: 47.5. Result ID: 69a9292d6dbb7075b951fc1e.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### AutoRefine-Base

EM: 46.7. Result ID: 69a9292d6dbb7075b951fc1c.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### O2-Searcher

EM: 44.4. Result ID: 69a9292d6dbb7075b951fc1a.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a784.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### AutoRefine-Instruct

EM: 43.6. Result ID: 69a9292d6dbb7075b951fc1b.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### ZeroSearch-Base

EM: 43. Result ID: 69a9292d6dbb7075b951fc19.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789d1e209131cea79568.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### ReSearch-Base

EM: 42.7. Result ID: 69a9292d6dbb7075b951fc18.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8a1e209131cea8902f.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### Search-R1-Base

EM: 42.1. Result ID: 69a9292d6dbb7075b951fc16.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e7b.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### InForage

EM: 42.1. Result ID: 69a9292d6dbb7075b951fc1d.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b841e209131cea88d2f.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### Search-R1-Instruct

EM: 39.7. Result ID: 69a9292d6dbb7075b951fc15.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e7b.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### ReSearch-Instruct

EM: 36.5. Result ID: 69a9292d6dbb7075b951fc17.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8a1e209131cea8902f.md>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### ProGraph-R1

EM: 35.94. Result ID: 69966f255698665ec4b61b72.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Graph-based knowledge"}. This record does not assert independent reproduction.

### Naive RAG

EM: 34.8. Result ID: 69a9292d6dbb7075b951fc12.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"Retrieval":"Workflow w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### ProGraph-R1

EM: 34.38. Result ID: 69966f255698665ec4b61b6a.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Graph-based knowledge"}. This record does not assert independent reproduction.

### Graph-R1

EM: 33.59. Result ID: 69966f255698665ec4b61b71.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a431e209131cea82033.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Graph-based knowledge"}. This record does not assert independent reproduction.

### Search-R1

EM: 32.03. Result ID: 69966f255698665ec4b61b6f.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e7b.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

### R1-Searcher

EM: 32.03. Result ID: 69966f255698665ec4b61b70.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea7356d.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

### Graph-R1

EM: 30.47. Result ID: 69966f255698665ec4b61b69.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a431e209131cea82033.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Graph-based knowledge"}. This record does not assert independent reproduction.

### SFT

EM: 24.9. Result ID: 69a9292d6dbb7075b951fc0f.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

Recorded evaluation configuration: {"Retrieval":"w/o Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### Search-R1

EM: 24.22. Result ID: 69966f255698665ec4b61b67.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e7b.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

### R1-Searcher

EM: 24.22. Result ID: 69966f255698665ec4b61b68.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea7356d.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

### Search-o1

EM: 23.8. Result ID: 69a9292d6dbb7075b951fc14.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Retrieval":"Agent w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### R1-Base

EM: 22.6. Result ID: 69a9292d6dbb7075b951fc11.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Retrieval":"w/o Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### R1-Instruct

EM: 21. Result ID: 69a9292d6dbb7075b951fc10.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Retrieval":"w/o Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### R1

EM: 16.41. Result ID: 69966f255698665ec4b61b6e.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### R1

EM: 11.72. Result ID: 69966f255698665ec4b61b66.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### IRCoT

EM: 11.1. Result ID: 69a9292d6dbb7075b951fc13.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fd81e209131cea4791d.md>)

[Implementation](<https://github.com/stonybrooknlp/ircot>)

Recorded evaluation configuration: {"Retrieval":"Workflow w/ Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### Direct Generation

EM: 10.6. Result ID: 69a9292d6dbb7075b951fc0e.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddc2d603e6de3e40587.md>)

Recorded evaluation configuration: {"Retrieval":"w/o Retrieval","Backbone":"Qwen2.5-3B"}. This record does not assert independent reproduction.

### SFT

EM: 5.12. Result ID: 69966f255698665ec4b61b6d.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Training","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### SFT

EM: 3.12. Result ID: 69966f255698665ec4b61b65.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Training","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### NaiveGeneration

EM: 2.34. Result ID: 69966f255698665ec4b61b63.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Prompt engineering","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### NaiveGeneration

EM: 1.56. Result ID: 69966f255698665ec4b61b6b.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Prompt engineering","Knowledge Interaction":"No knowledge interaction"}. This record does not assert independent reproduction.

### StandardRAG

EM: 1.56. Result ID: 69966f255698665ec4b61b6c.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B-Instruct","Optimization Method":"Prompt engineering","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

### StandardRAG

EM: 0. Result ID: 69966f255698665ec4b61b64.

[Reporting paper](<https://www.sota2.com/research/paper/69784684a2b28e761d87c4dc.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Optimization Method":"Prompt engineering","Knowledge Interaction":"Chunk-based knowledge"}. This record does not assert independent reproduction.

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