# Multi-Hop Question Answering on HotpotQA (Accuracy, Recall)

Source: [Multi-Hop Question Answering on HotpotQA (Accuracy, Recall)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-accuracy-recall>)

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

Data updated: 2026-06-17T08:01:47.814Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting Accuracy and Recall 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-Hop Question Answering |
| Dataset (including any stated split) | HotpotQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HyGRAG +Inference | 69.1 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HyGRAG | 68.72 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| RAPTOR-K | 61.24 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| EraRAG | 61.03 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| VanillaRAG | 60.97 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HippoRAG | 51.89 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| CoT | 27.77 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| Zero-shot | 27.36 | Not recorded | 6a322a5ad33dfb23e783eda0 |

### HyGRAG +Inference

Accuracy: 69.1. Result ID: 6a3253c1fbc373592c2fb0f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### HyGRAG

Accuracy: 68.72. Result ID: 6a3253c1fbc373592c2fb0f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### RAPTOR-K

Accuracy: 61.24. Result ID: 6a3253c1fbc373592c2fb0f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

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

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### EraRAG

Accuracy: 61.03. Result ID: 6a3253c1fbc373592c2fb0f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79da1e209131cea7fc22.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### VanillaRAG

Accuracy: 60.97. Result ID: 6a3253c1fbc373592c2fb0f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.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: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### HippoRAG

Accuracy: 51.89. Result ID: 6a3253c1fbc373592c2fb0f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76981e209131cea6dff9.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### CoT

Accuracy: 27.77. Result ID: 6a3253c1fbc373592c2fb0f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e781e209131cea4017d.md>)

[Implementation](<https://github.com/kojima-takeshi188/zero_shot_cot>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

### Zero-shot

Accuracy: 27.36. Result ID: 6a3253c1fbc373592c2fb0f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a5ad33dfb23e783eda0.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction.

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