# Audio Question on MMA-Bench

Source: [Audio Question on MMA-Bench](<https://www.sota2.com/research/sota/audio-question-on-mma-bench>)

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

Data updated: 2026-04-07T08:51:18.732Z

Evaluation of model performance on the MMA-Bench dataset for Audio Question tasks, including robustness metrics.

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 Question |
| Dataset (including any stated split) | MMA-Bench |
| 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-question-on-mma-bench.md?metric=Accuracy%20Clean>): Higher is better; unit: PERCENT.

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

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

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

## Recorded results

| Method | Accuracy Clean | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-2.5-Flash-Lite | 62.7 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Gemini-3.1-Flash-Lite-preview | 59.93 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Qwen3-Omni-30B | 57.39 | Not recorded | 69d48f7b7d0172140ec742a9 |
| Qwen2.5-Omni-7B | 46.6 | Not recorded | 69d48f7b7d0172140ec742a9 |
| ChatBridge | 41.61 | Not recorded | 69d48f7b7d0172140ec742a9 |
| PandaGPT | 13.12 | Not recorded | 69d48f7b7d0172140ec742a9 |

### Gemini-2.5-Flash-Lite

Accuracy Clean: 62.7. Result ID: 69d4c56847f34ce924bcab8b.

[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.

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

Accuracy Clean: 59.93. Result ID: 69d4c56847f34ce924bcab8c.

[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: 57.39. Result ID: 69d4c56847f34ce924bcab88.

[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: 46.6. Result ID: 69d4c56847f34ce924bcab87.

[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.

### ChatBridge

Accuracy Clean: 41.61. Result ID: 69d4c56847f34ce924bcab8a.

[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: 13.12. Result ID: 69d4c56847f34ce924bcab89.

[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.