# Runtime and Resource Usage for Knowledge Graph Question Answering on CWQ

Source: [Runtime and Resource Usage for Knowledge Graph Question Answering on CWQ](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq>)

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

Data updated: 2026-06-02T07:52:47.162Z

Evaluation focusing on the runtime performance and resource consumption (number of calls, input/output tokens) for Knowledge Graph Question Answering models tested on the Complex WebQuestions (CWQ) dataset.

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 | Knowledge Graph Question Answering |
| Dataset (including any stated split) | CWQ |
| Metric | # Calls |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [# Calls](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=%23%20Calls>): Lower is better; unit: SCALAR.

- [Runtime (s)](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=Runtime%20(s)>): Lower is better; unit: TIME.

- [Input Tokens](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=Input%20Tokens>): Higher is better; unit: SCALAR.

- [Output Tokens](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=Output%20Tokens>): Higher is better; unit: SCALAR.

- [Total Tokens](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=Total%20Tokens>): Higher is better; unit: SCALAR.

- [Total Cost ($)](<https://www.sota2.com/research/sota/runtime-and-resource-usage-for-knowledge-graph-question-answering-on-cwq.md?metric=Total%20Cost%20(%24)>): Lower is better; unit: OTHER.

## Recorded results

| Method | # Calls | Result date | Report paper |
| --- | --- | --- | --- |
| SubgraphRAG | 1 | Not recorded | 6a02b4afdbc836b87d824f3f |
| RAPL | 1 | Not recorded | 6a02b4afdbc836b87d824f3f |
| CoT | 1 | Not recorded | 691414752828b7cc6937e9ae |
| Logits-to-Logic | 1 | Not recorded | 691414752828b7cc6937e9ae |
| GCR | 2 | Not recorded | 6a02b4afdbc836b87d824f3f |
| PATHISE | 2 | Not recorded | 6a02b4afdbc836b87d824f3f |
| GCR | 2 | Not recorded | 691414752828b7cc6937e9ae |
| DP | 3.1 | Not recorded | 6a02b4afdbc836b87d824f3f |
| DoG | 5.7 | Not recorded | 691414752828b7cc6937e9ae |
| ToG | 9.2 | Not recorded | 691414752828b7cc6937e9ae |
| PoG | 13.3 | Not recorded | 691414752828b7cc6937e9ae |
| PoG | 13.9 | Not recorded | 6a02b4afdbc836b87d824f3f |

### SubgraphRAG

# Calls: 1. Result ID: 6a03596747f34ce924e8ea89.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77401e209131cea71faf.md>)

Recorded evaluation configuration: {"Stage":"Inference"}. This record does not assert independent reproduction.

### RAPL

# Calls: 1. Result ID: 6a03596747f34ce924e8ea8d.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79641e209131cea7d635.md>)

Recorded evaluation configuration: {"Stage":"Train Sup."}. This record does not assert independent reproduction.

### CoT

# Calls: 1. Result ID: 6a1e8bc6fbc373592c1873e8.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

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

### Logits-to-Logic

# Calls: 1. Result ID: 6a1e8bc6fbc373592c1873ed.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

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

### GCR

# Calls: 2. Result ID: 6a03596747f34ce924e8ea88.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d21e209131cea7a9a7.md>)

Recorded evaluation configuration: {"Stage":"Inference"}. This record does not assert independent reproduction.

### PATHISE

# Calls: 2. Result ID: 6a03596747f34ce924e8ea8c.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

Recorded evaluation configuration: {"Stage":"Inference"}. This record does not assert independent reproduction.

### GCR

# Calls: 2. Result ID: 6a1e8bc6fbc373592c1873eb.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d21e209131cea7a9a7.md>)

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

### DP

# Calls: 3.1. Result ID: 6a03596747f34ce924e8ea8b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c411e209131cea8d2fd.md>)

Recorded evaluation configuration: {"Stage":"Inference"}. This record does not assert independent reproduction.

### DoG

# Calls: 5.7. Result ID: 6a1e8bc6fbc373592c1873ea.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c21e209131cea63959.md>)

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

### ToG

# Calls: 9.2. Result ID: 6a1e8bc6fbc373592c1873e9.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a21e209131cea57b26.md>)

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

### PoG

# Calls: 13.3. Result ID: 6a1e8bc6fbc373592c1873ec.

[Reporting paper](<https://www.sota2.com/research/paper/691414752828b7cc6937e9ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75741e209131cea68054.md>)

[Implementation](<https://github.com/liyichen-cly/PoG>)

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

### PoG

# Calls: 13.9. Result ID: 6a03596747f34ce924e8ea8a.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4afdbc836b87d824f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75741e209131cea68054.md>)

[Implementation](<https://github.com/liyichen-cly/PoG>)

Recorded evaluation configuration: {"Stage":"Inference"}. This record does not assert independent reproduction.

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