# Knowledge Base Question Answering on CompWebQ

Source: [Knowledge Base Question Answering on CompWebQ](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-compwebq>)

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

Data updated: 2026-02-26T05:28:31.765Z

Evaluation of Knowledge Base Question Answering performance on the CompWebQ dataset, reporting Accuracy (Acc).

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) | CompWebQ |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/knowledge-base-question-answering-on-compwebq.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| T5-3B | 73.26 | Not recorded | 68fa6da71e209131cea3b2ed |
| T5-large | 71.38 | Not recorded | 68fa6da71e209131cea3b2ed |
| Das et al. (2021) | 70.4 | Not recorded | 68fa6da71e209131cea3b2ed |
| T5-base | 68.43 | Not recorded | 68fa6da71e209131cea3b2ed |

### T5-3B

Accuracy: 73.26. Result ID: 698fb4ec3a6c314849fb466d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Implementation](<https://github.com/hkunlp/unifiedskg>)

Recorded evaluation configuration: {"Backbone":"T5-3B"}. This record does not assert independent reproduction.

### T5-large

Accuracy: 71.38. Result ID: 698fb4ec3a6c314849fb466c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Implementation](<https://github.com/hkunlp/unifiedskg>)

Recorded evaluation configuration: {"Backbone":"T5-large"}. This record does not assert independent reproduction.

### Das et al. (2021)

Accuracy: 70.4. Result ID: 698fb4ec3a6c314849fb466e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

Recorded evaluation configuration: {"Extra Pre-training":false}. This record does not assert independent reproduction.

### T5-base

Accuracy: 68.43. Result ID: 698fb4ec3a6c314849fb466b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2ed.md>)

[Implementation](<https://github.com/hkunlp/unifiedskg>)

Recorded evaluation configuration: {"Backbone":"T5-base"}. This record does not assert independent reproduction.

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