# Question Answering on HotpotQA (F1, Performance Gain)

Source: [Question Answering on HotpotQA (F1, Performance Gain)](<https://www.sota2.com/research/sota/question-answering-on-hotpotqa-f1-performance-gain>)

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

Data updated: 2026-04-09T23:58:42.398Z

Evaluation of model performance on the HotpotQA dataset for Question Answering, specifically reporting F1 score and Performance Gain.

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 | Question Answering |
| Dataset (including any stated split) | HotpotQA |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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/question-answering-on-hotpotqa-f1-performance-gain.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Performance Gain](<https://www.sota2.com/research/sota/question-answering-on-hotpotqa-f1-performance-gain.md?metric=Performance%20Gain>): Higher is better; unit: SCALAR.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| PatchRAG | 53.2 | Not recorded | 69d732af7d0172140ec76c58 |
| RAFT | 49.4 | Not recorded | 69d732af7d0172140ec76c58 |
| Golden-only | 48.1 | Not recorded | 69d732af7d0172140ec76c58 |
| Auto-RAG | 44.9 | Not recorded | 69d732af7d0172140ec76c58 |
| PatchRAG | 44.8 | Not recorded | 69d732af7d0172140ec76c58 |
| ChatQA-1.5 | 44.6 | Not recorded | 69d732af7d0172140ec76c58 |
| RAFT | 44.6 | Not recorded | 69d732af7d0172140ec76c58 |
| Golden-only | 43.7 | Not recorded | 69d732af7d0172140ec76c58 |
| Self-RAG | 29.6 | Not recorded | 69d732af7d0172140ec76c58 |
| Standard RAG | 28.5 | Not recorded | 69d732af7d0172140ec76c58 |

### PatchRAG

F1 Score: 53.2. Result ID: 69d83d1e47f34ce924c028f3.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### RAFT

F1 Score: 49.4. Result ID: 69d83d1e47f34ce924c028f2.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d299.md>)

Recorded evaluation configuration: {"Step":"t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### Golden-only

F1 Score: 48.1. Result ID: 69d83d1e47f34ce924c028f1.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### Auto-RAG

F1 Score: 44.9. Result ID: 69d83d1e47f34ce924c028ec.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a6bd.md>)

Recorded evaluation configuration: {"Step":"-","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### PatchRAG

F1 Score: 44.8. Result ID: 69d83d1e47f34ce924c028f0.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"\< t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### ChatQA-1.5

F1 Score: 44.6. Result ID: 69d83d1e47f34ce924c028ed.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"-","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### RAFT

F1 Score: 44.6. Result ID: 69d83d1e47f34ce924c028ef.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d299.md>)

Recorded evaluation configuration: {"Step":"\< t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### Golden-only

F1 Score: 43.7. Result ID: 69d83d1e47f34ce924c028ee.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"\< t","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### Self-RAG

F1 Score: 29.6. Result ID: 69d83d1e47f34ce924c028eb.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dc1c.md>)

[Implementation](<https://selfrag.github.io/>)

Recorded evaluation configuration: {"Step":"-","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

### Standard RAG

F1 Score: 28.5. Result ID: 69d83d1e47f34ce924c028ea.

[Reporting paper](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58.md>)

Recorded evaluation configuration: {"Step":"-","Generator":"Llama-3 8B","Retriever":"bge-m3"}. This record does not assert independent reproduction.

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