# Speech-to-Speech Question Answering on AlpacaEval

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

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

Data updated: 2026-03-11T09:09:34.354Z

Evaluation of model performance on the AlpacaEval dataset for Speech-to-Speech Question Answering, measured using 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 | Speech-to-Speech Question Answering |
| Dataset (including any stated split) | AlpacaEval |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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/speech-to-speech-question-answering-on-alpacaeval.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VocalNet | 72.22 | Not recorded | 69b0f7312d603e6de3e46000 |
| Qwen2.5-Omni-7B | 67.17 | Not recorded | 69b0f7312d603e6de3e46000 |
| SPEECH-OMNI-LITE | 65.66 | Not recorded | 69b0f7312d603e6de3e46000 |
| LLaMA-Omni2 | 63.64 | Not recorded | 69b0f7312d603e6de3e46000 |
| GLM-4-Voice | 58.59 | Not recorded | 69b0f7312d603e6de3e46000 |
| Freeze-Omni | 28.79 | Not recorded | 69b0f7312d603e6de3e46000 |
| Baichuan-Omni-1.5 | 13.92 | Not recorded | 69b0f7312d603e6de3e46000 |

### VocalNet

Accuracy: 72.22. Result ID: 69b131466dbb7075b95bce32.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78361e209131cea773d2.md>)

Recorded evaluation configuration: {"Model Parameters":"8B"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Accuracy: 67.17. Result ID: 69b131466dbb7075b95bce36.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

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

Recorded evaluation configuration: {"Model Parameters":"7B"}. This record does not assert independent reproduction.

### SPEECH-OMNI-LITE

Accuracy: 65.66. Result ID: 69b131466dbb7075b95bce37.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

Recorded evaluation configuration: {"Model Parameters":"8B"}. This record does not assert independent reproduction.

### LLaMA-Omni2

Accuracy: 63.64. Result ID: 69b131466dbb7075b95bce33.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78671e209131cea783dc.md>)

Recorded evaluation configuration: {"Model Parameters":"7B"}. This record does not assert independent reproduction.

### GLM-4-Voice

Accuracy: 58.59. Result ID: 69b131466dbb7075b95bce31.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75f91e209131cea6abba.md>)

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

### Freeze-Omni

Accuracy: 28.79. Result ID: 69b131466dbb7075b95bce34.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa760a1e209131cea6b0d4.md>)

Recorded evaluation configuration: {"Model Parameters":"7B"}. This record does not assert independent reproduction.

### Baichuan-Omni-1.5

Accuracy: 13.92. Result ID: 69b131466dbb7075b95bce35.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7312d603e6de3e46000.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bc1e209131cea6ed2e.md>)

Recorded evaluation configuration: {"Model Parameters":"7B"}. This record does not assert independent reproduction.

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