# Helpfulness Assessment on AdvBench-audio Safe

Source: [Helpfulness Assessment on AdvBench-audio Safe](<https://www.sota2.com/research/sota/helpfulness-assessment-on-advbench-audio-safe>)

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

Data updated: 2026-05-08T08:27:23.242Z

Evaluation of model helpfulness using the AdvBench-audio Safe subset, measured by the BRR metric.

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 | Helpfulness Assessment |
| Dataset (including any stated split) | AdvBench-audio Safe |
| Metric | BRR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [BRR](<https://www.sota2.com/research/sota/helpfulness-assessment-on-advbench-audio-safe.md?metric=BRR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BRR | Result date | Report paper |
| --- | --- | --- | --- |
| RRS | 86.44 | Not recorded | 68fa7c5d1e209131cea8dc06 |
| No Defense | 85.19 | Not recorded | 68fa7c5d1e209131cea8dc06 |
| SARSteer | 85 | Not recorded | 68fa7c5d1e209131cea8dc06 |

### RRS

BRR: 86.44. Result ID: 69fd9df447f34ce924e09072.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dc06.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c11e209131cea7a528.md>)

Recorded evaluation configuration: {"Defense runtime (s)":"1145"}. This record does not assert independent reproduction.

### No Defense

BRR: 85.19. Result ID: 69fd9df447f34ce924e09071.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dc06.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SARSteer

BRR: 85. Result ID: 69fd9df447f34ce924e09073.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dc06.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dc06.md>)

Recorded evaluation configuration: {"Defense runtime (s)":"266"}. This record does not assert independent reproduction.

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