# Knowledge Base Question Answering on T-REx WikiData (test)

Source: [Knowledge Base Question Answering on T-REx WikiData (test)](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-t-rex-wikidata-test>)

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

Data updated: 2026-05-25T07:07:50.232Z

Evaluation of Knowledge Base Question Answering performance on the test split of the T-REx WikiData dataset, measured using Hits@1.

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 Base Question Answering |
| Dataset (including any stated split) | T-REx WikiData (test) |
| Metric | Hits@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 37 of 37 |
| 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

- [Hits@1](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-t-rex-wikidata-test.md?metric=Hits%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Hits@1 | Result date | Report paper |
| --- | --- | --- | --- |
| KG-R1 | 83.38 | Not recorded | 68fa7c031e209131cea8bde7 |
| KG-R1 | 80.1 | Not recorded | 68fa7c031e209131cea8bde7 |
| PoG | 79.52 | Not recorded | 68fa7c031e209131cea8bde7 |
| PoG | 78.75 | Not recorded | 68fa7c031e209131cea8bde7 |
| ReknoS | 78.17 | Not recorded | 68fa7c031e209131cea8bde7 |
| ReknoS | 77.11 | Not recorded | 68fa7c031e209131cea8bde7 |
| ReknoS | 77.05 | Not recorded | 68fa7c031e209131cea8bde7 |
| ToG | 77 | Not recorded | 68fa7c031e209131cea8bde7 |
| PoG | 75.69 | Not recorded | 68fa7c031e209131cea8bde7 |
| KG-Hopper w/Qwen-2.5-7B | 72.14 | Not recorded | 69c21a9c0636e5bf4afc496d |
| DeepSeek-R1-Distill-Llama-70B + KG | 72.04 | Not recorded | 69c21a9c0636e5bf4afc496d |
| LLaMA-3.1-8B (SFT) + KG | 70.23 | Not recorded | 69c21a9c0636e5bf4afc496d |
| GPT-4o-mini + KG | 69.7 | Not recorded | 69c21a9c0636e5bf4afc496d |
| Qwen-2.5-7B (SFT) + KG | 68.77 | Not recorded | 69c21a9c0636e5bf4afc496d |
| ToG | 67.93 | Not recorded | 68fa7c031e209131cea8bde7 |
| LLaMA-3.1-8B + KG | 65.8 | Not recorded | 69c21a9c0636e5bf4afc496d |
| LLaMA-3.3-70B + KG | 65.42 | Not recorded | 69c21a9c0636e5bf4afc496d |
| Qwen-2.5-7B + KG | 64.21 | Not recorded | 69c21a9c0636e5bf4afc496d |
| ToG | 58.55 | Not recorded | 68fa7c031e209131cea8bde7 |
| GPT-4o | 44.46 | Not recorded | 69c21a9c0636e5bf4afc496d |
| SC | 38.79 | Not recorded | 68fa7c031e209131cea8bde7 |
| CoT | 37.72 | Not recorded | 68fa7c031e209131cea8bde7 |
| RoG | 37.31 | Not recorded | 68fa7c031e209131cea8bde7 |
| IO | 34.61 | Not recorded | 68fa7c031e209131cea8bde7 |
| DeepSeek-R1-Distill-Llama-70B | 34.21 | Not recorded | 69c21a9c0636e5bf4afc496d |
| RoG | 32.5 | Not recorded | 68fa7c031e209131cea8bde7 |
| Qwen-2.5-7B | 31.15 | Not recorded | 69c21a9c0636e5bf4afc496d |
| GPT-4o-mini | 26.9 | Not recorded | 69c21a9c0636e5bf4afc496d |
| IO | 26.16 | Not recorded | 68fa7c031e209131cea8bde7 |
| SC | 26.01 | Not recorded | 68fa7c031e209131cea8bde7 |
| CoT | 24.48 | Not recorded | 68fa7c031e209131cea8bde7 |
| LLaMA-3.1-8B | 23 | Not recorded | 69c21a9c0636e5bf4afc496d |
| IO | 22.79 | Not recorded | 68fa7c031e209131cea8bde7 |
| RoG | 22.37 | Not recorded | 68fa7c031e209131cea8bde7 |
| LLaMA-3.3-70B | 20.12 | Not recorded | 69c21a9c0636e5bf4afc496d |
| SC | 20.01 | Not recorded | 68fa7c031e209131cea8bde7 |
| CoT | 17.38 | Not recorded | 68fa7c031e209131cea8bde7 |

### KG-R1

Hits@1: 83.38. Result ID: 6a13f534fbc373592c0aa9b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen2.5 3B","Training Dataset":"WebQSP"}. This record does not assert independent reproduction.

### KG-R1

Hits@1: 80.1. Result ID: 6a13f534fbc373592c0aa9b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen2.5 3B","Training Dataset":"CWQ"}. This record does not assert independent reproduction.

### PoG

Hits@1: 79.52. Result ID: 6a13f534fbc373592c0aa9aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### PoG

Hits@1: 78.75. Result ID: 6a13f534fbc373592c0aa9b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### ReknoS

Hits@1: 78.17. Result ID: 6a13f534fbc373592c0aa9a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b41e209131cea74e0b.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### ReknoS

Hits@1: 77.11. Result ID: 6a13f534fbc373592c0aa9ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b41e209131cea74e0b.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### ReknoS

Hits@1: 77.05. Result ID: 6a13f534fbc373592c0aa9b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b41e209131cea74e0b.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### ToG

Hits@1: 77. Result ID: 6a13f534fbc373592c0aa9b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### PoG

Hits@1: 75.69. Result ID: 6a13f534fbc373592c0aa9a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### KG-Hopper w/Qwen-2.5-7B

Hits@1: 72.14. Result ID: 69c2ac9047f34ce924abb4a5.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented with RL Fine-Tuning"}. This record does not assert independent reproduction.

### DeepSeek-R1-Distill-Llama-70B + KG

Hits@1: 72.04. Result ID: 69c2ac9047f34ce924abb4a1.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Size":"70B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction.

### LLaMA-3.1-8B (SFT) + KG

Hits@1: 70.23. Result ID: 69c2ac9047f34ce924abb4a4.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"8B","Strategy":"KG-Augmented with Supervised Fine-Tuning"}. This record does not assert independent reproduction.

### GPT-4o-mini + KG

Hits@1: 69.7. Result ID: 69c2ac9047f34ce924abb4a2.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction.

### Qwen-2.5-7B (SFT) + KG

Hits@1: 68.77. Result ID: 69c2ac9047f34ce924abb4a3.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented with Supervised Fine-Tuning"}. This record does not assert independent reproduction.

### ToG

Hits@1: 67.93. Result ID: 6a13f534fbc373592c0aa9a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### LLaMA-3.1-8B + KG

Hits@1: 65.8. Result ID: 69c2ac9047f34ce924abb49f.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"8B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction.

### LLaMA-3.3-70B + KG

Hits@1: 65.42. Result ID: 69c2ac9047f34ce924abb4a0.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"70B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction.

### Qwen-2.5-7B + KG

Hits@1: 64.21. Result ID: 69c2ac9047f34ce924abb49e.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction.

### ToG

Hits@1: 58.55. Result ID: 6a13f534fbc373592c0aa9a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### GPT-4o

Hits@1: 44.46. Result ID: 69c2ac9047f34ce924abb49d.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### SC

Hits@1: 38.79. Result ID: 6a13f534fbc373592c0aa9ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### CoT

Hits@1: 37.72. Result ID: 6a13f534fbc373592c0aa9ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### RoG

Hits@1: 37.31. Result ID: 6a13f534fbc373592c0aa9af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72591e209131cea55d71.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### IO

Hits@1: 34.61. Result ID: 6a13f534fbc373592c0aa9ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 3-235B"}. This record does not assert independent reproduction.

### DeepSeek-R1-Distill-Llama-70B

Hits@1: 34.21. Result ID: 69c2ac9047f34ce924abb49b.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Size":"70B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### RoG

Hits@1: 32.5. Result ID: 6a13f534fbc373592c0aa9a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72591e209131cea55d71.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### Qwen-2.5-7B

Hits@1: 31.15. Result ID: 69c2ac9047f34ce924abb498.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"7B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### GPT-4o-mini

Hits@1: 26.9. Result ID: 69c2ac9047f34ce924abb49c.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### IO

Hits@1: 26.16. Result ID: 6a13f534fbc373592c0aa9a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### SC

Hits@1: 26.01. Result ID: 6a13f534fbc373592c0aa9a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### CoT

Hits@1: 24.48. Result ID: 6a13f534fbc373592c0aa9a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-72B"}. This record does not assert independent reproduction.

### LLaMA-3.1-8B

Hits@1: 23. Result ID: 69c2ac9047f34ce924abb499.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"8B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### IO

Hits@1: 22.79. Result ID: 6a13f534fbc373592c0aa99e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### RoG

Hits@1: 22.37. Result ID: 6a13f534fbc373592c0aa9a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72591e209131cea55d71.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### LLaMA-3.3-70B

Hits@1: 20.12. Result ID: 69c2ac9047f34ce924abb49a.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a9c0636e5bf4afc496d.md>)

Recorded evaluation configuration: {"Size":"70B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction.

### SC

Hits@1: 20.01. Result ID: 6a13f534fbc373592c0aa9a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

### CoT

Hits@1: 17.38. Result ID: 6a13f534fbc373592c0aa99f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bde7.md>)

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

Recorded evaluation configuration: {"Backbone Model":"Qwen 2.5-7B"}. This record does not assert independent reproduction.

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