# Factual Question Answering on PopQA (Accuracy, Recall)

Source: [Factual Question Answering on PopQA (Accuracy, Recall)](<https://www.sota2.com/research/sota/factual-question-answering-on-popqa-accuracy-recall>)

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

Data updated: 2026-06-17T08:01:47.683Z

Evaluation of model performance on the PopQA dataset for Factual Question Answering, measured using Accuracy and 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 | Factual Question Answering |
| Dataset (including any stated split) | PopQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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/factual-question-answering-on-popqa-accuracy-recall.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HyGRAG +Inference | 72.38 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HyGRAG | 72.34 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HippoRAG2 | 68.12 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| L-LightRAG | 67.05 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| VanillaRAG | 66.98 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| RAPTOR | 66.33 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| RAPTOR-K | 66.26 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| EraRAG | 61.4 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HippoRAG | 55.18 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| L-GraphRAG | 54.82 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| HiRAG | 53.18 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| H-LightRAG | 47.46 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| ArchRAG | 30.81 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| G-LightRAG | 23.52 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| CoT | 16.03 | Not recorded | 6a322a5ad33dfb23e783eda0 |
| Zero-shot | 15.37 | Not recorded | 6a322a5ad33dfb23e783eda0 |

### HyGRAG +Inference

Accuracy: 72.38. Result ID: 6a3253c1fbc373592c2fb0bf.

[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","Retrieval top-k":"5","Embedding model":"BGE-M3"}. This record does not assert independent reproduction.

### HyGRAG

Accuracy: 72.34. Result ID: 6a3253c1fbc373592c2fb0be.

[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","Retrieval top-k":"5","Embedding model":"BGE-M3"}. This record does not assert independent reproduction.

### HippoRAG2

Accuracy: 68.12. Result ID: 6a3253c1fbc373592c2fb0ba.

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

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

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

### L-LightRAG

Accuracy: 67.05. Result ID: 6a3253c1fbc373592c2fb0b6.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa78461e209131cea778bd.md>)

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

### VanillaRAG

Accuracy: 66.98. Result ID: 6a3253c1fbc373592c2fb0b2.

[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","Retrieval top-k":"5","Embedding model":"BGE-M3","Chunk size":"1200 tokens"}. This record does not assert independent reproduction.

### RAPTOR

Accuracy: 66.33. Result ID: 6a3253c1fbc373592c2fb0b3.

[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","Retrieval top-k":"5","Embedding model":"BGE-M3"}. This record does not assert independent reproduction.

### RAPTOR-K

Accuracy: 66.26. Result ID: 6a3253c1fbc373592c2fb0b4.

[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","Retrieval top-k":"5","Embedding model":"BGE-M3","Clustering":"K-means"}. This record does not assert independent reproduction.

### EraRAG

Accuracy: 61.4. Result ID: 6a3253c1fbc373592c2fb0b5.

[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","Retrieval top-k":"5"}. This record does not assert independent reproduction.

### HippoRAG

Accuracy: 55.18. Result ID: 6a3253c1fbc373592c2fb0b9.

[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.

### L-GraphRAG

Accuracy: 54.82. Result ID: 6a3253c1fbc373592c2fb0bb.

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

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

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

### HiRAG

Accuracy: 53.18. Result ID: 6a3253c1fbc373592c2fb0bc.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89746.md>)

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

### H-LightRAG

Accuracy: 47.46. Result ID: 6a3253c1fbc373592c2fb0b8.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa78461e209131cea778bd.md>)

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

### ArchRAG

Accuracy: 30.81. Result ID: 6a3253c1fbc373592c2fb0bd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a7f1e209131cea8380f.md>)

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

### G-LightRAG

Accuracy: 23.52. Result ID: 6a3253c1fbc373592c2fb0b7.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa78461e209131cea778bd.md>)

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

### CoT

Accuracy: 16.03. Result ID: 6a3253c1fbc373592c2fb0b1.

[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","Decoding strategy":"greedy decoding"}. This record does not assert independent reproduction.

### Zero-shot

Accuracy: 15.37. Result ID: 6a3253c1fbc373592c2fb0b0.

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

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

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