# Mobile Power Management on PowerLens-Bench

Source: [Mobile Power Management on PowerLens-Bench](<https://www.sota2.com/research/sota/mobile-power-management-on-powerlens-bench>)

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

Data updated: 2026-03-23T10:44:10.387Z

Evaluation of models on the PowerLens-Bench dataset focusing on mobile power management strategies, measured by Action Accuracy, Energy Saving, Violation Rate, and User Experience Score.

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 | Mobile Power Management |
| Dataset (including any stated split) | PowerLens-Bench |
| Metric | Action 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

- [Action Accuracy](<https://www.sota2.com/research/sota/mobile-power-management-on-powerlens-bench.md?metric=Action%20Accuracy>): Higher is better; unit: PERCENT.

- [Energy Saving](<https://www.sota2.com/research/sota/mobile-power-management-on-powerlens-bench.md?metric=Energy%20Saving>): Higher is better; unit: PERCENT.

- [Violation Rate](<https://www.sota2.com/research/sota/mobile-power-management-on-powerlens-bench.md?metric=Violation%20Rate>): Lower is better; unit: PERCENT.

- [User Experience Score](<https://www.sota2.com/research/sota/mobile-power-management-on-powerlens-bench.md?metric=User%20Experience%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Action Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PowerLens | 81.7 | Not recorded | 69c0c90f0636e5bf4afc3c79 |
| Rule-Based | 63.5 | Not recorded | 69c0c90f0636e5bf4afc3c79 |
| Single-Agent LLM | 52.1 | Not recorded | 69c0c90f0636e5bf4afc3c79 |
| Battery Saver | 48.3 | Not recorded | 69c0c90f0636e5bf4afc3c79 |

### PowerLens

Action Accuracy: 81.7. Result ID: 69c117a547f34ce924a9412d.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c90f0636e5bf4afc3c79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c90f0636e5bf4afc3c79.md>)

Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash"}. This record does not assert independent reproduction.

### Rule-Based

Action Accuracy: 63.5. Result ID: 69c117a547f34ce924a9412b.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c90f0636e5bf4afc3c79.md>)

Recorded evaluation configuration: {"Description":"Static per-category rules without LLM reasoning"}. This record does not assert independent reproduction.

### Single-Agent LLM

Action Accuracy: 52.1. Result ID: 69c117a547f34ce924a9412c.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c90f0636e5bf4afc3c79.md>)

Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Configuration":"Monolithic prompt without multi-agent decomposition"}. This record does not assert independent reproduction.

### Battery Saver

Action Accuracy: 48.3. Result ID: 69c117a547f34ce924a9412a.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c90f0636e5bf4afc3c79.md>)

Recorded evaluation configuration: {"Description":"Android's built-in low-power mode"}. This record does not assert independent reproduction.

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