# Multi-hop Question Answering on HotpotQA (Answer EM/F1, Support EM/F1)

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

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

Data updated: 2026-02-26T05:34:56.513Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting Exact Match (EM) and F1 scores separately for the final answer and the supporting evidence.

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 | Answer EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

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

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

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

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

## Recorded results

| Method | Answer EM | Result date | Report paper |
| --- | --- | --- | --- |
| MoE-DiffuSeq | 72.88 | Not recorded | 694b739d53fdd5c361739bf0 |
| Longformer | 71.21 | Not recorded | 694b739d53fdd5c361739bf0 |
| DiffuSeq | 70.91 | Not recorded | 694b739d53fdd5c361739bf0 |

### MoE-DiffuSeq

Answer EM: 72.88. Result ID: 6996b2a25698665ec4fcf5d6.

[Reporting paper](<https://www.sota2.com/research/paper/694b739d53fdd5c361739bf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694b739d53fdd5c361739bf0.md>)

Recorded evaluation configuration: {"MoE":"true","Sparse Attention":"true"}. This record does not assert independent reproduction.

### Longformer

Answer EM: 71.21. Result ID: 6996b2a25698665ec4fcf5d4.

[Reporting paper](<https://www.sota2.com/research/paper/694b739d53fdd5c361739bf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e701.md>)

[Implementation](<https://github.com/allenai/longformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DiffuSeq

Answer EM: 70.91. Result ID: 6996b2a25698665ec4fcf5d5.

[Reporting paper](<https://www.sota2.com/research/paper/694b739d53fdd5c361739bf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4df0b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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