# Graph Question Answering Suite (ExplaGraphs, SceneGraphs, WebQSP)

Source: [Graph Question Answering Suite (ExplaGraphs, SceneGraphs, WebQSP)](<https://www.sota2.com/research/sota/graph-question-answering-suite-explagraphs-scenegraphs-webqsp>)

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

Data updated: 2026-05-19T10:22:12.630Z

Evaluation of model performance on Graph Question Answering across the ExplaGraphs, SceneGraphs, and WebQSP datasets.

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 | Graph Question Answering |
| Dataset (including any stated split) | GraphQA ExplaGraphs, SceneGraphs, WebQSP |
| Metric | Expla Graphs Score |
| 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

- [Expla Graphs Score](<https://www.sota2.com/research/sota/graph-question-answering-suite-explagraphs-scenegraphs-webqsp.md?metric=Expla%20Graphs%20Score>): Higher is better; unit: PERCENT.

- [SceneGraphs Score](<https://www.sota2.com/research/sota/graph-question-answering-suite-explagraphs-scenegraphs-webqsp.md?metric=SceneGraphs%20Score>): Higher is better; unit: PERCENT.

- [WebQSP Score](<https://www.sota2.com/research/sota/graph-question-answering-suite-explagraphs-scenegraphs-webqsp.md?metric=WebQSP%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/graph-question-answering-suite-explagraphs-scenegraphs-webqsp.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Expla Graphs Score | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 90.07 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| G-Retriever | 85.16 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| Graph Token | 85.08 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| KAPING | 62.27 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| CoT-BAG | 57.94 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| Prompt Tuning | 57.63 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| Zero-CoT | 57.04 | Not recorded | 68fa76cb1e209131cea6f1c4 |
| Zero-Shot | 56.5 | Not recorded | 68fa76cb1e209131cea6f1c4 |

### Ours

Expla Graphs Score: 90.07. Result ID: 6a0c37ccfbc373592c02e406.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Frozen LLM w/ PT","# of Prompt Tokens":"8"}. This record does not assert independent reproduction.

### G-Retriever

Expla Graphs Score: 85.16. Result ID: 6a0c37ccfbc373592c02e405.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73541e209131cea5bdef.md>)

[Implementation](<https://github.com/XiaoxinHe/G-Retriever>)

Recorded evaluation configuration: {"Evaluation Protocol":"Frozen LLM w/ PT","# of Prompt Tokens":"1"}. This record does not assert independent reproduction.

### Graph Token

Expla Graphs Score: 85.08. Result ID: 6a0c37ccfbc373592c02e404.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72261e209131cea54caa.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Frozen LLM w/ PT","# of Prompt Tokens":"1"}. This record does not assert independent reproduction.

### KAPING

Expla Graphs Score: 62.27. Result ID: 6a0c37ccfbc373592c02e402.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f9c1e209131cea46999.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Inference Only","# of Prompt Tokens":"-"}. This record does not assert independent reproduction.

### CoT-BAG

Expla Graphs Score: 57.94. Result ID: 6a0c37ccfbc373592c02e401.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71b31e209131cea529a4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Inference Only","# of Prompt Tokens":"-"}. This record does not assert independent reproduction.

### Prompt Tuning

Expla Graphs Score: 57.63. Result ID: 6a0c37ccfbc373592c02e403.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa51e209131cea296c9.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Frozen LLM w/ PT","# of Prompt Tokens":"10"}. This record does not assert independent reproduction.

### Zero-CoT

Expla Graphs Score: 57.04. Result ID: 6a0c37ccfbc373592c02e400.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"Inference Only","# of Prompt Tokens":"-"}. This record does not assert independent reproduction.

### Zero-Shot

Expla Graphs Score: 56.5. Result ID: 6a0c37ccfbc373592c02e3ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76cb1e209131cea6f1c4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Inference Only","# of Prompt Tokens":"-"}. This record does not assert independent reproduction.

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