DATASETS2SCOVAL BENCHMARK ROTATIONACTIVE
s2s-workflow-bank-hard-v1 speech-to-speech benchmark dataset
s2s-workflow-bank-hard-v1 is a speech-to-speech test set in Coval's daily rotation — every measured speech-to-speech model runs the same fixed inputs from it.
- Models measured
- 10
- last 30 days
How models rank on s2s-workflow-bank-hard-v1
Full S2S dashboardmedian of all models · 1224 ms
| # | Model | Host | V2V | Samples |
|---|---|---|---|---|
| 1 | Prism | Rime | 789 ms | 30 |
| 2 | Gemini 3.1 Flash Live (Preview) | 1041 ms | 140 | |
| 3 | Gemini 3.8 Live | 1050 ms | 141 | |
| 4 | Dialog Rsn 1 | PolyAI | 1093 ms | 72 |
| 5 | Phonic 1 | Phonic | 1155 ms | 96 |
| 6 | Qwen3.8 Omni Flash Realtime | Alibaba | 1292 ms | 120 |
| 7 | GPT-Live-1 | OpenAI | 1399 ms | 89 |
| 8 | Eleven Realtime v1 Mini | ElevenLabs | 1627 ms | 120 |
| 9 | Eleven Realtime v1 Max | ElevenLabs | 1674 ms | 120 |
| 10 | Grok Voice 3.0 | SpaceXAI | 1815 ms | 120 |
Metrics reported for this dataset
Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.
Evaluate your own voice agent
Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.