# Multi-hop Question Answering on HotpotQA (EM, F1, Acc)

Source: [Multi-hop Question Answering on HotpotQA (EM, F1, Acc)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-acc>)

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

Data updated: 2026-02-27T10:42:53.517Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting Exact Match (EM), F1 score, and 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) | HotpotQA |
| Metric | Exact Match (EM) |
| 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

- [Exact Match (EM)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-acc.md?metric=Exact%20Match%20(EM)>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-acc.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy (Acc)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-acc.md?metric=Accuracy%20(Acc)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Exact Match (EM) | Result date | Report paper |
| --- | --- | --- | --- |
| CompactRAG GPT-4-Reading | 49.6 | Not recorded | 698575cbc97a0b3e3b5d5df5 |
| Iter-RetGen | 46.8 | Not recorded | 698575cbc97a0b3e3b5d5df5 |
| CompactRAG LLaMA-3.1-8b-Reading | 45.2 | Not recorded | 698575cbc97a0b3e3b5d5df5 |
| IRCoT | 42.8 | Not recorded | 698575cbc97a0b3e3b5d5df5 |
| Vanilla-RAG | 27.6 | Not recorded | 698575cbc97a0b3e3b5d5df5 |
| Self-Ask | 23.6 | Not recorded | 698575cbc97a0b3e3b5d5df5 |

### CompactRAG GPT-4-Reading

Exact Match (EM): 49.6. Result ID: 69a1752b35dfcabb00e72801.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

Recorded evaluation configuration: {"Token / Sample":"1.9K"}. This record does not assert independent reproduction.

### Iter-RetGen

Exact Match (EM): 46.8. Result ID: 69a1752b35dfcabb00e727ff.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e48a.md>)

Recorded evaluation configuration: {"Token / Sample":"4.7K"}. This record does not assert independent reproduction.

### CompactRAG LLaMA-3.1-8b-Reading

Exact Match (EM): 45.2. Result ID: 69a1752b35dfcabb00e72800.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

Recorded evaluation configuration: {"Token / Sample":"1.9K"}. This record does not assert independent reproduction.

### IRCoT

Exact Match (EM): 42.8. Result ID: 69a1752b35dfcabb00e727fe.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

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

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

Recorded evaluation configuration: {"Token / Sample":"10.2K"}. This record does not assert independent reproduction.

### Vanilla-RAG

Exact Match (EM): 27.6. Result ID: 69a1752b35dfcabb00e727fc.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.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: {"Token / Sample":"2.7K"}. This record does not assert independent reproduction.

### Self-Ask

Exact Match (EM): 23.6. Result ID: 69a1752b35dfcabb00e727fd.

[Reporting paper](<https://www.sota2.com/research/paper/698575cbc97a0b3e3b5d5df5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ef1e209131cea4e227.md>)

[Implementation](<https://github.com/ofirpress/self-ask>)

Recorded evaluation configuration: {"Token / Sample":"6.9K"}. This record does not assert independent reproduction.

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