# Open-domain Question Answering on NQ single-hop (test)

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

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

Data updated: 2026-02-26T05:36:30.968Z

Evaluation of Open-domain Question Answering performance specifically on the single-hop subset of the NQ test set.

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) | NQ single-hop (test) |
| Metric | Avg@16 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Avg@16](<https://www.sota2.com/research/sota/open-domain-question-answering-on-nq-single-hop-test.md?metric=Avg%4016>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/open-domain-question-answering-on-nq-single-hop-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

- [Tokens](<https://www.sota2.com/research/sota/open-domain-question-answering-on-nq-single-hop-test.md?metric=Tokens>): Higher is better; unit: SCALAR.

- [Pass@16](<https://www.sota2.com/research/sota/open-domain-question-answering-on-nq-single-hop-test.md?metric=Pass%4016>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg@16 | Result date | Report paper |
| --- | --- | --- | --- |
| Dr. MAS | 47.7 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| Dr. MAS | 47.4 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 46.4 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 45.2 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| Dr. MAS | 44.6 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| Dr. MAS | 43.8 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 43.8 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 41 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 40.6 | Not recorded | 698abc3fc97a0b3e3b5de549 |
| GRPO | 27.1 | Not recorded | 698abc3fc97a0b3e3b5de549 |

### Dr. MAS

Avg@16: 47.7. Result ID: 6998d3695698665ec4372125.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Implementation](<https://github.com/langfengQ/DrMAS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Agent Configuration":"Multi-Agent & LLM Non-Sharing"}. This record does not assert independent reproduction.

### Dr. MAS

Avg@16: 47.4. Result ID: 6998d3695698665ec4372123.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Implementation](<https://github.com/langfengQ/DrMAS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Agent Configuration":"Multi-Agent & LLM Sharing"}. This record does not assert independent reproduction.

### GRPO

Avg@16: 46.4. Result ID: 6998d3695698665ec4372121.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Agent Configuration":"Single-Agent"}. This record does not assert independent reproduction.

### GRPO

Avg@16: 45.2. Result ID: 6998d3695698665ec4372122.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Agent Configuration":"Multi-Agent & LLM Sharing"}. This record does not assert independent reproduction.

### Dr. MAS

Avg@16: 44.6. Result ID: 6998d3695698665ec4372120.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Implementation](<https://github.com/langfengQ/DrMAS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B","Agent Configuration":"Multi-Agent & LLM Non-Sharing"}. This record does not assert independent reproduction.

### Dr. MAS

Avg@16: 43.8. Result ID: 6998d3695698665ec437211e.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

[Implementation](<https://github.com/langfengQ/DrMAS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B","Agent Configuration":"Multi-Agent & LLM Sharing"}. This record does not assert independent reproduction.

### GRPO

Avg@16: 43.8. Result ID: 6998d3695698665ec437211f.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B","Agent Configuration":"Multi-Agent & LLM Non-Sharing"}. This record does not assert independent reproduction.

### GRPO

Avg@16: 41. Result ID: 6998d3695698665ec437211d.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B","Agent Configuration":"Multi-Agent & LLM Sharing"}. This record does not assert independent reproduction.

### GRPO

Avg@16: 40.6. Result ID: 6998d3695698665ec437211c.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

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

### GRPO

Avg@16: 27.1. Result ID: 6998d3695698665ec4372124.

[Reporting paper](<https://www.sota2.com/research/paper/698abc3fc97a0b3e3b5de549.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Agent Configuration":"Multi-Agent & LLM Non-Sharing"}. This record does not assert independent reproduction.

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