# Speech Question Answering on VoiceBench AlpacaEval

Source: [Speech Question Answering on VoiceBench AlpacaEval](<https://www.sota2.com/research/sota/speech-question-answering-on-voicebench-alpacaeval>)

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

Data updated: 2026-05-01T07:45:32.129Z

Evaluation of model performance on the VoiceBench AlpacaEval dataset for Speech Question Answering, measured using the AlpacaEval score (1-5).

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 | Speech Question Answering |
| Dataset (including any stated split) | VoiceBench AlpacaEval |
| Metric | AlpacaEval Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [AlpacaEval Score](<https://www.sota2.com/research/sota/speech-question-answering-on-voicebench-alpacaeval.md?metric=AlpacaEval%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AlpacaEval Score | Result date | Report paper |
| --- | --- | --- | --- |
| MiniCPM-o 4.5 | 4.81 | Not recorded | 69f4337355a3c32af89fd045 |
| Qwen3-Omni | 4.74 | Not recorded | 69f4337355a3c32af89fd045 |
| Kimi-Audio | 4.46 | Not recorded | 69f4337355a3c32af89fd045 |

### MiniCPM-o 4.5

AlpacaEval Score: 4.81. Result ID: 69f45a1547f34ce924d9fef1.

[Reporting paper](<https://www.sota2.com/research/paper/69f4337355a3c32af89fd045.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f4337355a3c32af89fd045.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-o>)

Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction.

### Qwen3-Omni

AlpacaEval Score: 4.74. Result ID: 69f45a1547f34ce924d9fef0.

[Reporting paper](<https://www.sota2.com/research/paper/69f4337355a3c32af89fd045.md>)

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

Recorded evaluation configuration: {"Size":"30B-A3B"}. This record does not assert independent reproduction.

### Kimi-Audio

AlpacaEval Score: 4.46. Result ID: 69f45a1547f34ce924d9feef.

[Reporting paper](<https://www.sota2.com/research/paper/69f4337355a3c32af89fd045.md>)

Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction.

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