# Multi-hop Question Answering on HotpotQA (F1)

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

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

Data updated: 2026-02-26T05:43:46.723Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, specifically reporting the F1 score.

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 | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

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

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| AdaptOrch | 76.4 | Not recorded | 6997eaad09c33900fcd766e1 |
| Self-MoA (matched) | 75.5 | Not recorded | 6997eaad09c33900fcd766e1 |
| Static-Parallel | 72.8 | Not recorded | 6997eaad09c33900fcd766e1 |
| MoA-3L | 71.6 | Not recorded | 6997eaad09c33900fcd766e1 |
| LLM-Blender | 70.4 | Not recorded | 6997eaad09c33900fcd766e1 |
| Static-Sequential | 69.1 | Not recorded | 6997eaad09c33900fcd766e1 |
| Single Best | 68.3 | Not recorded | 6997eaad09c33900fcd766e1 |

### AdaptOrch

F1 Score: 76.4. Result ID: 699b007a5698665ec4925f4d.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

Recorded evaluation configuration: {"Lat.":"1.3×","Tok(K)":"22.7"}. This record does not assert independent reproduction.

### Self-MoA (matched)

F1 Score: 75.5. Result ID: 699b007a5698665ec4925f4c.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d31e209131cea6f549.md>)

Recorded evaluation configuration: {"Lat.":"1.2×","Tok(K)":"23.1"}. This record does not assert independent reproduction.

### Static-Parallel

F1 Score: 72.8. Result ID: 699b007a5698665ec4925f49.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

Recorded evaluation configuration: {"Lat.":"1.2×","Tok(K)":"28.4"}. This record does not assert independent reproduction.

### MoA-3L

F1 Score: 71.6. Result ID: 699b007a5698665ec4925f48.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73821e209131cea5cd56.md>)

Recorded evaluation configuration: {"Lat.":"2.5×","Tok(K)":"47.3"}. This record does not assert independent reproduction.

### LLM-Blender

F1 Score: 70.4. Result ID: 699b007a5698665ec4925f4b.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fa8.md>)

Recorded evaluation configuration: {"Lat.":"1.5×","Tok(K)":"34.8"}. This record does not assert independent reproduction.

### Static-Sequential

F1 Score: 69.1. Result ID: 699b007a5698665ec4925f4a.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

Recorded evaluation configuration: {"Lat.":"2.1×","Tok(K)":"26.1"}. This record does not assert independent reproduction.

### Single Best

F1 Score: 68.3. Result ID: 699b007a5698665ec4925f47.

[Reporting paper](<https://www.sota2.com/research/paper/6997eaad09c33900fcd766e1.md>)

Recorded evaluation configuration: {"Lat.":"1.0×","Tok(K)":"6.8"}. This record does not assert independent reproduction.

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