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

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

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

Data updated: 2026-03-05T07:27:26.799Z

Evaluation of model performance on the full HotpotQA dataset for multi-hop question answering, reporting Exact Match (EM) and 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 (full) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

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

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

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| Gold Context | 69.2 | Not recorded | 69a90ddd2d603e6de3e4058a |
| PLUGMEM | 61.4 | Not recorded | 69a90ddd2d603e6de3e4058a |
| HippoRAG2 | 60 | Not recorded | 69a90ddd2d603e6de3e4058a |
| PropRAG | 57.8 | Not recorded | 69a90ddd2d603e6de3e4058a |
| RAPTOR | 56.7 | Not recorded | 69a90ddd2d603e6de3e4058a |
| GraphRAG | 55.2 | Not recorded | 69a90ddd2d603e6de3e4058a |
| Vanilla Retrieval | 51.7 | Not recorded | 69a90ddd2d603e6de3e4058a |
| A-Mem | 43.8 | Not recorded | 69a90ddd2d603e6de3e4058a |
| No Context | 22.1 | Not recorded | 69a90ddd2d603e6de3e4058a |

### Gold Context

EM: 69.2. Result ID: 69a92ed76dbb7075b95227aa.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

Recorded evaluation configuration: {"LLM":"Q32","#TokAvg.":"86.5","Info. Density":"1.6e-1"}. This record does not assert independent reproduction.

### PLUGMEM

EM: 61.4. Result ID: 69a92ed76dbb7075b95227b1.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"81.6","Info. Density":"1.4e-1"}. This record does not assert independent reproduction.

### HippoRAG2

EM: 60. Result ID: 69a92ed76dbb7075b95227b0.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de8a.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"595.1","Info. Density":"1.9e-2"}. This record does not assert independent reproduction.

### PropRAG

EM: 57.8. Result ID: 69a92ed76dbb7075b95227af.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd71e209131cea8ad8a.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"626.1","Info. Density":"1.9e-2"}. This record does not assert independent reproduction.

### RAPTOR

EM: 56.7. Result ID: 69a92ed76dbb7075b95227ae.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fe1e209131cea53fc2.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"806.3","Info. Density":"1.1e-2"}. This record does not assert independent reproduction.

### GraphRAG

EM: 55.2. Result ID: 69a92ed76dbb7075b95227ad.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770d1e209131cea70c5a.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"L70"}. This record does not assert independent reproduction.

### Vanilla Retrieval

EM: 51.7. Result ID: 69a92ed76dbb7075b95227ab.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.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: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"659.2","Info. Density":"1.2e-2"}. This record does not assert independent reproduction.

### A-Mem

EM: 43.8. Result ID: 69a92ed76dbb7075b95227ac.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf31e209131cea8b869.md>)

Recorded evaluation configuration: {"Emb":"NVE","LLM":"Q32","#TokAvg.":"695.6","Info. Density":"1.2e-2"}. This record does not assert independent reproduction.

### No Context

EM: 22.1. Result ID: 69a92ed76dbb7075b95227a9.

[Reporting paper](<https://www.sota2.com/research/paper/69a90ddd2d603e6de3e4058a.md>)

Recorded evaluation configuration: {"LLM":"Q32"}. This record does not assert independent reproduction.

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