# Audio-Visual Question on WorldSense (Robustness Evaluation)

Source: [Audio-Visual Question on WorldSense (Robustness Evaluation)](<https://www.sota2.com/research/sota/audio-visual-question-on-worldsense-robustness-evaluation>)

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

Data updated: 2026-04-07T08:51:18.755Z

Evaluation of model performance on the WorldSense dataset for Audio-Visual Question tasks, specifically measuring accuracy and ASR under both clean and adversarial attack conditions.

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 | Audio-Visual Question |
| Dataset (including any stated split) | WorldSense |
| Metric | Accuracy (Clean) |
| 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 (Clean)](<https://www.sota2.com/research/sota/audio-visual-question-on-worldsense-robustness-evaluation.md?metric=Accuracy%20(Clean)>): Higher is better; unit: PERCENT.

- [Accuracy (Attack)](<https://www.sota2.com/research/sota/audio-visual-question-on-worldsense-robustness-evaluation.md?metric=Accuracy%20(Attack)>): Higher is better; unit: PERCENT.

- [ASR Score (Clean)](<https://www.sota2.com/research/sota/audio-visual-question-on-worldsense-robustness-evaluation.md?metric=ASR%20Score%20(Clean)>): Higher is better; unit: PERCENT.

- [ASR Score (Attack)](<https://www.sota2.com/research/sota/audio-visual-question-on-worldsense-robustness-evaluation.md?metric=ASR%20Score%20(Attack)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Clean) | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-3.1-Flash-Lite-preview | 59.7 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Qwen3-Omni-30B | 55.72 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Qwen2.5-Omni-7B | 49.9 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Gemini-2.5-Flash-Lite | 49.33 | Not recorded | 69d48f7b7d0172140ec742a9 |
| ChatBridge | 33.57 | Not recorded | 69d48f7b7d0172140ec742a9 |
| PandaGPT | 29.48 | Not recorded | 69d48f7b7d0172140ec742a9 |

### Gemini-3.1-Flash-Lite-preview

Accuracy (Clean): 59.7. Result ID: 69d4c56847f34ce924bcaba4.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

Recorded evaluation configuration: {"Model":"Gemini-3.1-Flash-Lite-preview"}. This record does not assert independent reproduction.

### Qwen3-Omni-30B

Accuracy (Clean): 55.72. Result ID: 69d4c56847f34ce924bcaba0.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

Recorded evaluation configuration: {"Model":"Qwen3-Omni-30B"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Accuracy (Clean): 49.9. Result ID: 69d4c56847f34ce924bcab9f.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Omni-7B"}. This record does not assert independent reproduction.

### Gemini-2.5-Flash-Lite

Accuracy (Clean): 49.33. Result ID: 69d4c56847f34ce924bcaba3.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

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

### ChatBridge

Accuracy (Clean): 33.57. Result ID: 69d4c56847f34ce924bcaba2.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

Recorded evaluation configuration: {"Model":"ChatBridge"}. This record does not assert independent reproduction.

### PandaGPT

Accuracy (Clean): 29.48. Result ID: 69d4c56847f34ce924bcaba1.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f7b7d0172140ec742a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea46009.md>)

Recorded evaluation configuration: {"Model":"PandaGPT"}. This record does not assert independent reproduction.

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