# Auditory Understanding on AIR-Bench foundation

Source: [Auditory Understanding on AIR-Bench foundation](<https://www.sota2.com/research/sota/auditory-understanding-on-air-bench-foundation>)

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

Data updated: 2026-06-08T07:02:15.255Z

Evaluation of model performance on the AIR-Bench foundation dataset focusing on general Auditory Understanding capabilities, measured by Accuracy.

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 | Auditory Understanding |
| Dataset (including any stated split) | AIR-Bench foundation |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/auditory-understanding-on-air-bench-foundation.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SpectCount (Audio Flamingo 3) | 64.85 | Not recorded | 6a264c9890966ade919bea95 |
| Audio Flamingo 3 | 64.16 | Not recorded | 6a264c9890966ade919bea95 |
| SpectCount (Qwen2-Audio-Instruct) | 62.78 | Not recorded | 6a264c9890966ade919bea95 |
| Qwen2-Audio-Instruct | 60.17 | Not recorded | 6a264c9890966ade919bea95 |

### SpectCount (Audio Flamingo 3)

Accuracy: 64.85. Result ID: 6a2668b5fbc373592c22a3cd.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

Recorded evaluation configuration: {"Size":"8.3B","Trained Parameters":"26.2M","Setting":"SpectCount"}. This record does not assert independent reproduction.

### Audio Flamingo 3

Accuracy: 64.16. Result ID: 6a2668b5fbc373592c22a3cc.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

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

Recorded evaluation configuration: {"Size":"8.3B","Setting":"Base (reproduced)"}. This record does not assert independent reproduction.

### SpectCount (Qwen2-Audio-Instruct)

Accuracy: 62.78. Result ID: 6a2668b5fbc373592c22a3cf.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

Recorded evaluation configuration: {"Size":"8.4B","Trained Parameters":"25.9M","Setting":"SpectCount"}. This record does not assert independent reproduction.

### Qwen2-Audio-Instruct

Accuracy: 60.17. Result ID: 6a2668b5fbc373592c22a3ce.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c9890966ade919bea95.md>)

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

Recorded evaluation configuration: {"Size":"8.4B","Setting":"Base (reproduced)"}. This record does not assert independent reproduction.

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