Spoken understanding and reasoning on URO-Bench English Basic
92.7U ScoreStep-Audio 2
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Step-Audio 22026.05 | 92.7 | 76.5 | 84.9 | 83.9 | |
| GPT-4o-Audio2026.05 | 90.2 | 75.9 | 90.4 | 84.5 | |
| GPT-Realtime2026.05 | 87.4 | 84.1 | 94.1 | 88.1 | |
| Kimi-Audio2026.05 | 83.4 | 42.3 | 60.4 | 60 | |
| Listen-Write-Speak2026.05 | 83.3 | 69.6 | 92.7 | 81.9 | |
| Listen-Write-Speak (w/o write while listen)visible writing during listening=disabled2026.05 | 76.6 | 72.2 | 92.4 | 80.4 | |
| Listen-Write-Speak (w/o write while speak)visible writing during speaking=disabled2026.05 | 74.8 | 72.2 | 66.3 | 71.1 | |
| Qwen-Omni2026.05 | 66.3 | 69.6 | 76.2 | 70.6 |