# Spoken Question Answering on AlpacaEval

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

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

Data updated: 2026-05-12T15:00:24.936Z

Evaluation of model performance on the AlpacaEval dataset for Spoken Question Answering, measured using WER and UTMOS.

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 | Spoken Question Answering |
| Dataset (including any stated split) | AlpacaEval |
| Metric | WER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [WER](<https://www.sota2.com/research/sota/spoken-question-answering-on-alpacaeval.md?metric=WER>): Lower is better; unit: PERCENT.

- [UTMOS](<https://www.sota2.com/research/sota/spoken-question-answering-on-alpacaeval.md?metric=UTMOS>): Higher is better; unit: SCALAR.

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

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

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| LLaMA-Omni2 | 3.88 | Not recorded | 69b0f7312d603e6de3e46000 |
| Qwen2.5-Omni-7B | 5.54 | Not recorded | 69b0f7312d603e6de3e46000 |
| VocalNet | 7.43 | Not recorded | 69b0f7312d603e6de3e46000 |
| SPEECH-OMNI-LITE | 23.77 | Not recorded | 69b0f7312d603e6de3e46000 |
| GLM-4-Voice | 29.44 | Not recorded | 69b0f7312d603e6de3e46000 |
| Freeze-Omni | 49.47 | Not recorded | 69b0f7312d603e6de3e46000 |
| Baichuan-Omni-1.5 | 86.53 | Not recorded | 69b0f7312d603e6de3e46000 |

### LLaMA-Omni2

WER: 3.88. Result ID: 69b131466dbb7075b95bce4f.

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

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

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

### Qwen2.5-Omni-7B

WER: 5.54. Result ID: 69b131466dbb7075b95bce52.

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

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

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

### VocalNet

WER: 7.43. Result ID: 69b131466dbb7075b95bce4e.

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

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

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

### SPEECH-OMNI-LITE

WER: 23.77. Result ID: 69b131466dbb7075b95bce53.

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

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

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

### GLM-4-Voice

WER: 29.44. Result ID: 69b131466dbb7075b95bce4d.

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

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

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

### Freeze-Omni

WER: 49.47. Result ID: 69b131466dbb7075b95bce50.

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

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

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

### Baichuan-Omni-1.5

WER: 86.53. Result ID: 69b131466dbb7075b95bce51.

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

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

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

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