DATASETS2SCOVAL BENCHMARK ROTATIONACTIVE

Ultra Bank caller speech-to-speech benchmark dataset

Ultra Bank caller 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
2
last 30 days
Current leader · V2V#1 / 2
1227ms
Gemini 3.1 Flash Live (Preview)via Google

How models rank on Ultra Bank caller

Full S2S dashboard
Voice-to-Voice Latency on Ultra Bank callerMilliseconds · lower is better · 30-day average on this datasetEvery S2S model measured on the Ultra Bank caller dataset, ranked on Voice-to-Voice Latency.
median of all models · 1368 ms
S2S models on the Ultra Bank caller dataset over the last 30 days, ranked on Voice-to-Voice Latency.
#ModelHostV2VInstruction adherenceSamples
1Gemini 3.1 Flash Live (Preview)Google1227 ms94%250
2GPT Realtime 2OpenAI1509 ms86%252
Under-sampled models are excluded; tied models share a place.

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.

Book a Demo