# Multi-step Question Answering on MuSiQue (test)

Source: [Multi-step Question Answering on MuSiQue (test)](<https://www.sota2.com/research/sota/multi-step-question-answering-on-musique-test>)

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

Data updated: 2026-02-26T05:42:28.572Z

Evaluation of model performance on the test split of the MuSiQue dataset specifically for Multi-step Question Answering tasks, reporting Exact Match (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 | Multi-step Question Answering |
| Dataset (including any stated split) | MuSiQue (test) |
| Metric | Exact Match |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Exact Match](<https://www.sota2.com/research/sota/multi-step-question-answering-on-musique-test.md?metric=Exact%20Match>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Exact Match | Result date | Report paper |
| --- | --- | --- | --- |
| KeyExtract + CoopRAG | 53.8 | Not recorded | 693ba1666cfd488761a55038 |
| KeyExtract + CoopRAG | 52.5 | Not recorded | 693ba1666cfd488761a55038 |
| IRCoT + CoopRAG | 52.3 | Not recorded | 693ba1666cfd488761a55038 |
| IRCoT + HippoRAG | 21.9 | Not recorded | 693ba1666cfd488761a55038 |
| IRCoT + ColBERTv2 | 19.1 | Not recorded | 693ba1666cfd488761a55038 |

### KeyExtract + CoopRAG

Exact Match: 53.8. Result ID: 6996c4615698665ec40fc8d7.

[Reporting paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

Recorded evaluation configuration: {"Reader (LLM)":"GPT-4o-mini"}. This record does not assert independent reproduction.

### KeyExtract + CoopRAG

Exact Match: 52.5. Result ID: 6996c4615698665ec40fc8d6.

[Reporting paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

Recorded evaluation configuration: {"Reader (LLM)":"Gemma2-9B"}. This record does not assert independent reproduction.

### IRCoT + CoopRAG

Exact Match: 52.3. Result ID: 6996c4615698665ec40fc8d5.

[Reporting paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

Recorded evaluation configuration: {"Reader (LLM)":"GPT-4o-mini"}. This record does not assert independent reproduction.

### IRCoT + HippoRAG

Exact Match: 21.9. Result ID: 6996c4615698665ec40fc8d4.

[Reporting paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

Recorded evaluation configuration: {"Reader (LLM)":"GPT-3.5-turbo"}. This record does not assert independent reproduction.

### IRCoT + ColBERTv2

Exact Match: 19.1. Result ID: 6996c4615698665ec40fc8d3.

[Reporting paper](<https://www.sota2.com/research/paper/693ba1666cfd488761a55038.md>)

Recorded evaluation configuration: {"Reader (LLM)":"GPT-4o-mini"}. This record does not assert independent reproduction.

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