# Boolean Question Answering on BoolQ (ET, ES, E\*S, AR%)

Source: [Boolean Question Answering on BoolQ (ET, ES, E\*S, AR%)](<https://www.sota2.com/research/sota/boolean-question-answering-on-boolq-et-es-e-s-ar-percent>)

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

Data updated: 2026-06-04T11:09:31.753Z

Evaluation of model performance on the BoolQ dataset for Boolean Question Answering, measured using ET, ES, E\*S, and AR%.

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 | Boolean Question Answering |
| Dataset (including any stated split) | BoolQ |
| Metric | E\*S Score |
| 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

- [E\*S Score](<https://www.sota2.com/research/sota/boolean-question-answering-on-boolq-et-es-e-s-ar-percent.md?metric=E*S%20Score>): Higher is better; unit: PERCENT.

- [ET Score](<https://www.sota2.com/research/sota/boolean-question-answering-on-boolq-et-es-e-s-ar-percent.md?metric=ET%20Score>): Higher is better; unit: PERCENT.

- [ES Score](<https://www.sota2.com/research/sota/boolean-question-answering-on-boolq-et-es-e-s-ar-percent.md?metric=ES%20Score>): Higher is better; unit: PERCENT.

- [AR (Accuracy Rate)](<https://www.sota2.com/research/sota/boolean-question-answering-on-boolq-et-es-e-s-ar-percent.md?metric=AR%20(Accuracy%20Rate)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | E\*S Score | Result date | Report paper |
| --- | --- | --- | --- |
| Recover-LoRA | 82.5 | Not recorded | 6a2106cec10484bac23f03e7 |
| Recover-LoRA | 82 | Not recorded | 6a2106cec10484bac23f03e7 |

### Recover-LoRA

E\*S Score: 82.5. Result ID: 6a215c8cfbc373592c1dfd98.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106cec10484bac23f03e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106cec10484bac23f03e7.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Quantization":"W2-GateUp","Training Data Source":"Synthetic-10k","Training Samples":"10k"}. This record does not assert independent reproduction.

### Recover-LoRA

E\*S Score: 82. Result ID: 6a215c8cfbc373592c1dfd97.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106cec10484bac23f03e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106cec10484bac23f03e7.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Quantization":"W2-GateUp","Training Data Source":"OpenHermes-10k","Training Samples":"10k"}. This record does not assert independent reproduction.

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