DATASETS2SCOVAL BENCHMARK ROTATIONACTIVE
s2s-workflow-bank-extra-hard-v1 speech-to-speech benchmark dataset
s2s-workflow-bank-extra-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-extra-hard-v1
Full S2S dashboardmedian of all models · 1407 ms
| # | Model | Host | V2V | Samples |
|---|---|---|---|---|
| 1 | Dialog Rsn 1 | PolyAI | 897 ms | 71 |
| 2 | Prism | Rime | 1054 ms | 27 |
| 3 | Qwen3.8 Omni Flash Realtime | Alibaba | 1211 ms | 120 |
| 4 | GPT-Live-1 | OpenAI | 1321 ms | 90 |
| 5 | Phonic 1 | Phonic | 1343 ms | 96 |
| 6 | Eleven Realtime v1 Mini | ElevenLabs | 1470 ms | 120 |
| 7 | Eleven Realtime v1 Max | ElevenLabs | 1472 ms | 118 |
| 8 | Gemini 3.1 Flash Live (Preview) | 1514 ms | 143 | |
| 9 | Gemini 3.8 Live | 1670 ms | 144 | |
| 10 | Grok Voice 3.0 | SpaceXAI | 1824 ms | 118 |
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.