# Audio-Language Understanding (MCQ) on MMAU-Pro 1.0 (test)

Source: [Audio-Language Understanding (MCQ) on MMAU-Pro 1.0 (test)](<https://www.sota2.com/research/sota/audio-language-understanding-mcq-on-mmau-pro-1-0-test>)

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

Data updated: 2026-04-28T10:21:24.887Z

Evaluation of Audio-Language Understanding capabilities using Multiple Choice Questions (MCQ) on the test split of the MMAU-Pro 1.0 dataset, reporting Accuracy and Text-prior rate (RTP).

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-Language Understanding (MCQ) |
| Dataset (including any stated split) | MMAU-Pro 1.0 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 27 of 27 |
| 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](<https://www.sota2.com/research/sota/audio-language-understanding-mcq-on-mmau-pro-1-0-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Text-prior Rate (RTP)](<https://www.sota2.com/research/sota/audio-language-understanding-mcq-on-mmau-pro-1-0-test.md?metric=Text-prior%20Rate%20(RTP)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-Omni (I) | 59.5 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2.5-Omni-7B | 57.7 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen3-Omni (T) | 56.5 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Audio-Flamingo-3 | 52.7 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2-Audio-7B | 44.8 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Audio-Flamingo-3 | 44.1 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Phi-4-Multimodal | 43.7 | Not recorded | 69f03f7a55a3c32af89fa542 |
| DeSTA-2.5 | 43.5 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen3-Omni (I) | 43.2 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Voxtral-Mini-3B | 41.7 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen3-Omni (I) | 41 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen3-Omni (T) | 40.5 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2.5-Omni-7B | 39.3 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen3-Omni (T) | 33.8 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2-Audio-7B | 31.4 | Not recorded | 69f03f7a55a3c32af89fa542 |
| DeSTA-2.5 | 31.3 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Audio-Flamingo-3 | 31.2 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2.5-Omni-7B | 31.2 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Voxtral-Mini-3B | 30 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Phi-4-Multimodal | 29.9 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Phi-4-Multimodal | 28.6 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Qwen2-Audio-7B | 28.2 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Chance Level | 25.9 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Chance Level | 25.9 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Chance Level | 25.9 | Not recorded | 69f03f7a55a3c32af89fa542 |
| DeSTA-2.5 | 20.3 | Not recorded | 69f03f7a55a3c32af89fa542 |
| Voxtral-Mini-3B | 20 | Not recorded | 69f03f7a55a3c32af89fa542 |

### Qwen3-Omni (I)

Accuracy: 59.5. Result ID: 69f089b247f34ce924d71f94.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Accuracy: 57.7. Result ID: 69f089b247f34ce924d71f91.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Size":"10.7B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Qwen3-Omni (T)

Accuracy: 56.5. Result ID: 69f089b247f34ce924d71f97.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Audio-Flamingo-3

Accuracy: 52.7. Result ID: 69f089b247f34ce924d71f85.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4d1e209131cea82504.md>)

Recorded evaluation configuration: {"Size":"8.4B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Qwen2-Audio-7B

Accuracy: 44.8. Result ID: 69f089b247f34ce924d71f8e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

Recorded evaluation configuration: {"Size":"8.2B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Audio-Flamingo-3

Accuracy: 44.1. Result ID: 69f089b247f34ce924d71f86.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4d1e209131cea82504.md>)

Recorded evaluation configuration: {"Size":"8.4B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Phi-4-Multimodal

Accuracy: 43.7. Result ID: 69f089b247f34ce924d71f8b.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72272.md>)

Recorded evaluation configuration: {"Size":"5.6B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### DeSTA-2.5

Accuracy: 43.5. Result ID: 69f089b247f34ce924d71f88.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fae2.md>)

Recorded evaluation configuration: {"Size":"8.8B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Qwen3-Omni (I)

Accuracy: 43.2. Result ID: 69f089b247f34ce924d71f95.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Voxtral-Mini-3B

Accuracy: 41.7. Result ID: 69f089b247f34ce924d71f9a.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1c1e209131cea813c5.md>)

Recorded evaluation configuration: {"Size":"4.7B","Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Qwen3-Omni (I)

Accuracy: 41. Result ID: 69f089b247f34ce924d71f96.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Qwen3-Omni (T)

Accuracy: 40.5. Result ID: 69f089b247f34ce924d71f98.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Accuracy: 39.3. Result ID: 69f089b247f34ce924d71f92.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Size":"10.7B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Qwen3-Omni (T)

Accuracy: 33.8. Result ID: 69f089b247f34ce924d71f99.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Size":"30B†","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Qwen2-Audio-7B

Accuracy: 31.4. Result ID: 69f089b247f34ce924d71f8f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

Recorded evaluation configuration: {"Size":"8.2B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### DeSTA-2.5

Accuracy: 31.3. Result ID: 69f089b247f34ce924d71f89.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fae2.md>)

Recorded evaluation configuration: {"Size":"8.8B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Audio-Flamingo-3

Accuracy: 31.2. Result ID: 69f089b247f34ce924d71f87.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4d1e209131cea82504.md>)

Recorded evaluation configuration: {"Size":"8.4B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Accuracy: 31.2. Result ID: 69f089b247f34ce924d71f93.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Size":"10.7B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Voxtral-Mini-3B

Accuracy: 30. Result ID: 69f089b247f34ce924d71f9b.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1c1e209131cea813c5.md>)

Recorded evaluation configuration: {"Size":"4.7B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Phi-4-Multimodal

Accuracy: 29.9. Result ID: 69f089b247f34ce924d71f8d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72272.md>)

Recorded evaluation configuration: {"Size":"5.6B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Phi-4-Multimodal

Accuracy: 28.6. Result ID: 69f089b247f34ce924d71f8c.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72272.md>)

Recorded evaluation configuration: {"Size":"5.6B","Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Qwen2-Audio-7B

Accuracy: 28.2. Result ID: 69f089b247f34ce924d71f90.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

Recorded evaluation configuration: {"Size":"8.2B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Chance Level

Accuracy: 25.9. Result ID: 69f089b247f34ce924d71f9d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

Recorded evaluation configuration: {"Size":null,"Evaluation Protocol":"Full"}. This record does not assert independent reproduction.

### Chance Level

Accuracy: 25.9. Result ID: 69f089b247f34ce924d71f9e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

Recorded evaluation configuration: {"Size":null,"Evaluation Protocol":"None"}. This record does not assert independent reproduction.

### Chance Level

Accuracy: 25.9. Result ID: 69f089b247f34ce924d71f9f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

Recorded evaluation configuration: {"Size":null,"Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### DeSTA-2.5

Accuracy: 20.3. Result ID: 69f089b247f34ce924d71f8a.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7fae2.md>)

Recorded evaluation configuration: {"Size":"8.8B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

### Voxtral-Mini-3B

Accuracy: 20. Result ID: 69f089b247f34ce924d71f9c.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7a55a3c32af89fa542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1c1e209131cea813c5.md>)

Recorded evaluation configuration: {"Size":"4.7B","Evaluation Protocol":"TB"}. This record does not assert independent reproduction.

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