# Multi-Hop Question Answering on MuSiQue (out-of-domain)

Source: [Multi-Hop Question Answering on MuSiQue (out-of-domain)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-out-of-domain>)

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

Data updated: 2026-02-27T11:58:19.212Z

Evaluation of model performance on the out-of-domain subset of the MuSiQue dataset for Multi-Hop Question Answering, measured using Accuracy.

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 | Multi-Hop Question Answering |
| Dataset (including any stated split) | MuSiQue (out-of-domain) |
| Metric | Accuracy |
| 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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| StepSearch | 22.6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| SKILLRL | 20.2 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| ZeroSearch | 18.4 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| EvolveR | 15.6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| Search-R1 | 14.6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| RAG | 9.4 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| Search-o1 | 8.6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| CoT | 6.6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| R1-Instruct | 6 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |
| Qwen2.5 | 4.8 | Not recorded | 698abbd1c97a0b3e3b5de1d0 |

### StepSearch

Accuracy: 22.6. Result ID: 69a186c935dfcabb00e7a1a5.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a76a.md>)

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

### SKILLRL

Accuracy: 20.2. Result ID: 69a186c935dfcabb00e7a1a7.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

[Implementation](<https://github.com/aiming-lab/SkillRL>)

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

### ZeroSearch

Accuracy: 18.4. Result ID: 69a186c935dfcabb00e7a1a4.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

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

### EvolveR

Accuracy: 15.6. Result ID: 69a186c935dfcabb00e7a1a6.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5c1e209131cea8dbe7.md>)

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

### Search-R1

Accuracy: 14.6. Result ID: 69a186c935dfcabb00e7a1a3.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

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

### RAG

Accuracy: 9.4. Result ID: 69a186c935dfcabb00e7a1a0.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

### Search-o1

Accuracy: 8.6. Result ID: 69a186c935dfcabb00e7a1a1.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

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

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

### CoT

Accuracy: 6.6. Result ID: 69a186c935dfcabb00e7a19f.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

### R1-Instruct

Accuracy: 6. Result ID: 69a186c935dfcabb00e7a1a2.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

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

### Qwen2.5

Accuracy: 4.8. Result ID: 69a186c935dfcabb00e7a19e.

[Reporting paper](<https://www.sota2.com/research/paper/698abbd1c97a0b3e3b5de1d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cdc5.md>)

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

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