# Visual Question Answering on OmniDrive

Source: [Visual Question Answering on OmniDrive](<https://www.sota2.com/research/sota/visual-question-answering-on-omnidrive>)

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

Data updated: 2026-03-17T11:13:47.016Z

Evaluation of model performance on the OmniDrive dataset for Visual Question Answering tasks, measured by the Perception 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 | Visual Question Answering |
| Dataset (including any stated split) | OmniDrive |
| Metric | Perception 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

- [Perception Score](<https://www.sota2.com/research/sota/visual-question-answering-on-omnidrive.md?metric=Perception%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Perception Score | Result date | Report paper |
| --- | --- | --- | --- |
| AutoMoT | 89 | Not recorded | 69b8e0590636e5bf4afbef3f |
| ReCogDrive | 82 | Not recorded | 69b8e0590636e5bf4afbef3f |
| Robotron-Drive | 82 | Not recorded | 69b8e0590636e5bf4afbef3f |
| OpenEMMA | 43 | Not recorded | 69b8e0590636e5bf4afbef3f |

### AutoMoT

Perception Score: 89. Result ID: 69b9375547f34ce924a2d65a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0590636e5bf4afbef3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0590636e5bf4afbef3f.md>)

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

### ReCogDrive

Perception Score: 82. Result ID: 69b9375547f34ce924a2d657.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0590636e5bf4afbef3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89839.md>)

[Implementation](<https://github.com/xiaomi-research/recogdrive>)

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

### Robotron-Drive

Perception Score: 82. Result ID: 69b9375547f34ce924a2d658.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0590636e5bf4afbef3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a741e209131cea835a8.md>)

Recorded evaluation configuration: {"reproduced":"true"}. This record does not assert independent reproduction.

### OpenEMMA

Perception Score: 43. Result ID: 69b9375547f34ce924a2d659.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0590636e5bf4afbef3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77071e209131cea709b4.md>)

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

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