# Multi-hop Question Answering on HotpotQA (FCR, JSR)

Source: [Multi-hop Question Answering on HotpotQA (FCR, JSR)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-fcr-jsr>)

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

Data updated: 2026-02-26T05:44:04.052Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, specifically measured using FCR (Full Context Recall) and JSR (Joint Span Recall).

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 | FCR |
| 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

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

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

## Recorded results

| Method | FCR | Result date | Report paper |
| --- | --- | --- | --- |
| CatRAG | 80.4 | Not recorded | 6981819ba8b01e76cc8e26db |
| HippoRAG 2 | 75.5 | Not recorded | 6981819ba8b01e76cc8e26db |
| text-embedding-3-small | 64.9 | Not recorded | 6981819ba8b01e76cc8e26db |
| RAPTOR | 61.4 | Not recorded | 6981819ba8b01e76cc8e26db |
| Contriever | 54.1 | Not recorded | 6981819ba8b01e76cc8e26db |
| GTR (T5-base) | 53 | Not recorded | 6981819ba8b01e76cc8e26db |
| BM25 | 38.3 | Not recorded | 6981819ba8b01e76cc8e26db |

### CatRAG

FCR: 80.4. Result ID: 6996542d5698665ec4993ff2.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

Recorded evaluation configuration: {"Retrieval Category":"Structure-Aware RAG"}. This record does not assert independent reproduction.

### HippoRAG 2

FCR: 75.5. Result ID: 6996542d5698665ec4993ff1.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

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

Recorded evaluation configuration: {"Retrieval Category":"Structure-Aware RAG"}. This record does not assert independent reproduction.

### text-embedding-3-small

FCR: 64.9. Result ID: 6996542d5698665ec4993fef.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

Recorded evaluation configuration: {"Retrieval Category":"Standard Retrieval"}. This record does not assert independent reproduction.

### RAPTOR

FCR: 61.4. Result ID: 6996542d5698665ec4993ff0.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

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

Recorded evaluation configuration: {"Retrieval Category":"Structure-Aware RAG"}. This record does not assert independent reproduction.

### Contriever

FCR: 54.1. Result ID: 6996542d5698665ec4993fed.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4b1e209131cea38d50.md>)

[Implementation](<https://github.com/facebookresearch/contriever>)

Recorded evaluation configuration: {"Retrieval Category":"Standard Retrieval"}. This record does not assert independent reproduction.

### GTR (T5-base)

FCR: 53. Result ID: 6996542d5698665ec4993fee.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b671e209131cea2e15a.md>)

[Implementation](<https://tfhub.dev/google/collections/gtr/1>)

Recorded evaluation configuration: {"Retrieval Category":"Standard Retrieval"}. This record does not assert independent reproduction.

### BM25

FCR: 38.3. Result ID: 6996542d5698665ec4993fec.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ba8b01e76cc8e26db.md>)

Recorded evaluation configuration: {"Retrieval Category":"Standard Retrieval"}. This record does not assert independent reproduction.

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