# Spoken understanding and reasoning on URO-Bench English Pro

Source: [Spoken understanding and reasoning on URO-Bench English Pro](<https://www.sota2.com/research/sota/spoken-understanding-and-reasoning-on-uro-bench-english-pro>)

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

Data updated: 2026-06-09T06:22:43.431Z

Evaluation of spoken understanding and reasoning capabilities using the URO-Bench English Pro dataset, measured by U, R, O, and Average scores.

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 understanding and reasoning |
| Dataset (including any stated split) | URO-Bench English Pro |
| Metric | U Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [U Score](<https://www.sota2.com/research/sota/spoken-understanding-and-reasoning-on-uro-bench-english-pro.md?metric=U%20Score>): Higher is better; unit: PERCENT.

- [R Score](<https://www.sota2.com/research/sota/spoken-understanding-and-reasoning-on-uro-bench-english-pro.md?metric=R%20Score>): Higher is better; unit: PERCENT.

- [O Score](<https://www.sota2.com/research/sota/spoken-understanding-and-reasoning-on-uro-bench-english-pro.md?metric=O%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/spoken-understanding-and-reasoning-on-uro-bench-english-pro.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | U Score | Result date | Report paper |
| --- | --- | --- | --- |
| Listen-Write-Speak (w/o write while listen) | 75.4 | Not recorded | 6a279e0890966ade919bf642 |
| Listen-Write-Speak | 74.6 | Not recorded | 6a279e0890966ade919bf642 |
| Listen-Write-Speak (w/o write while speak) | 73 | Not recorded | 6a279e0890966ade919bf642 |
| Step-Audio 2 | 64.9 | Not recorded | 6a279e0890966ade919bf642 |
| GPT-4o-Audio | 60.7 | Not recorded | 6a279e0890966ade919bf642 |
| GPT-Realtime | 59.7 | Not recorded | 6a279e0890966ade919bf642 |
| Kimi-Audio | 50.3 | Not recorded | 6a279e0890966ade919bf642 |
| Qwen-Omni | 44.5 | Not recorded | 6a279e0890966ade919bf642 |

### Listen-Write-Speak (w/o write while listen)

U Score: 75.4. Result ID: 6a27b03cfbc373592c23a73d.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Implementation](<https://github.com/zly-idleness/lws_demo>)

Recorded evaluation configuration: {"visible writing during listening":"disabled"}. This record does not assert independent reproduction.

### Listen-Write-Speak

U Score: 74.6. Result ID: 6a27b03cfbc373592c23a73c.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Implementation](<https://github.com/zly-idleness/lws_demo>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Listen-Write-Speak (w/o write while speak)

U Score: 73. Result ID: 6a27b03cfbc373592c23a73e.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Implementation](<https://github.com/zly-idleness/lws_demo>)

Recorded evaluation configuration: {"visible writing during speaking":"disabled"}. This record does not assert independent reproduction.

### Step-Audio 2

U Score: 64.9. Result ID: 6a27b03cfbc373592c23a73b.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b021e209131cea8635d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o-Audio

U Score: 60.7. Result ID: 6a27b03cfbc373592c23a737.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-Realtime

U Score: 59.7. Result ID: 6a27b03cfbc373592c23a738.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Kimi-Audio

U Score: 50.3. Result ID: 6a27b03cfbc373592c23a739.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78431e209131cea77803.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-Omni

U Score: 44.5. Result ID: 6a27b03cfbc373592c23a73a.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e0890966ade919bf642.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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