# Open-domain Question Answering on ComplexWebQuestions (CWQ) (dev)

Source: [Open-domain Question Answering on ComplexWebQuestions (CWQ) (dev)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-complexwebquestions-cwq-dev>)

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

Data updated: 2026-02-26T05:28:15.073Z

Evaluation of model performance on the development split of the ComplexWebQuestions (CWQ) dataset for Open-domain Question Answering, measured using Accuracy.

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 | Open-domain Question Answering |
| Dataset (including any stated split) | ComplexWebQuestions (CWQ) (dev) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/open-domain-question-answering-on-complexwebquestions-cwq-dev.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TOME-2 | 47.7 | Not recorded | 68fa6c521e209131cea3340f |
| REALM | 46.7 | Not recorded | 68fa6c521e209131cea3340f |
| TOME-1 | 44.9 | Not recorded | 68fa6c521e209131cea3340f |
| Entities as Experts | 42.7 | Not recorded | 68fa6c521e209131cea3340f |
| OPQL | 41.1 | Not recorded | 68fa6c521e209131cea3340f |
| T5-3B | 38.7 | Not recorded | 68fa6c521e209131cea3340f |

### TOME-2

Accuracy: 47.7. Result ID: 698effb13a6c314849f47d26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Implementation](<https://github.com/google-research/language/tree/master/language/mentionmemory>)

Recorded evaluation configuration: {"#Params":"220M","#Encoded":"1"}. This record does not assert independent reproduction.

### REALM

Accuracy: 46.7. Result ID: 698effb13a6c314849f47d21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

Recorded evaluation configuration: {"#Params":"330M","#Encoded":"5"}. This record does not assert independent reproduction.

### TOME-1

Accuracy: 44.9. Result ID: 698effb13a6c314849f47d25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Implementation](<https://github.com/google-research/language/tree/master/language/mentionmemory>)

Recorded evaluation configuration: {"#Params":"220M","#Encoded":"1"}. This record does not assert independent reproduction.

### Entities as Experts

Accuracy: 42.7. Result ID: 698effb13a6c314849f47d23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686c1e209131cea1c100.md>)

Recorded evaluation configuration: {"#Params":"360M","#Encoded":"1"}. This record does not assert independent reproduction.

### OPQL

Accuracy: 41.1. Result ID: 698effb13a6c314849f47d24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2b1e209131cea268f9.md>)

Recorded evaluation configuration: {"#Params":"220M","#Encoded":"1"}. This record does not assert independent reproduction.

### T5-3B

Accuracy: 38.7. Result ID: 698effb13a6c314849f47d22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea3340f.md>)

Recorded evaluation configuration: {"#Params":"3B","#Encoded":"1"}. This record does not assert independent reproduction.

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