Gemini 3.1 Flash Live Preview
- Reliable on bookings.
- Model
- models/gemini-3.1-flash-live-preview
- Setting
- Thinking level high
- Voice
- Charon
- Turn taking
- Shared local turn detection
- Audio
- 16 kHz
- Cost
- Averaged over the calls with a usage record.
Phonic v1 is ahead on reliability, success rate, agent responses, stalled calls and response time, and Gemini 3.1 Flash Live Preview on data accuracy, interruption and cost.
Last updated Methodology by Dileep Chagam
Pick Gemini 3.1 Flash Live Preview for saving the caller's data correctly (1.8 points higher), handling interruptions (0.09 higher) and lower cost ($0.070 cheaper). Pick Phonic v1 for reliability across repeated calls (6.1 points higher), calls that pass every check (1.2 points higher), getting the agent's replies right (2.0 points higher), fewer stalled calls (3.3 points lower) and fast replies (1.28s sooner).
Scenarios that passed on all three runs.
Phonic v1, 6.1 points higher
Calls that passed every check.
Phonic v1, 1.2 points higher
Calls where the agent's replies reached the expected outcome.
Phonic v1, 2.0 points higher
Calls where everything the agent saved matched exactly.
Gemini 3.1 Flash Live, 1.8 points higher
Calls where the agent went silent for 10 seconds or more.
Phonic v1, 3.3 points lower
How well it handled being talked over, 0 to 5.
Gemini 3.1 Flash Live, 0.09 higher
Median time to start replying after the caller finishes.
Phonic v1, 1.28s sooner
One minute of call at the vendor's published rates.
Gemini 3.1 Flash Live, $0.070 cheaper
The small figure is the place among ranked models. The cascade is not ranked.
Phonic v1 1.60s, Gemini 3.1 Flash Live 2.88s at the median.
Phonic v1 is more reliable, by 6.1 points. Gemini 3.1 Flash Live Preview passed 51 of 82 scenarios on all three runs, and Phonic v1 passed 56. A scenario only counts when every run of it passed.
For a phone agent, Phonic v1, since it gets more scenarios right on every run. Phonic v1 is ahead on reliability, success rate, agent responses, stalled calls and response time, and Gemini 3.1 Flash Live Preview on data accuracy, interruption and cost.
Gemini 3.1 Flash Live Preview, by 1.8 points. Gemini 3.1 Flash Live Preview saved everything exactly right on 79.2% of the calls that save data, and Phonic v1 on 77.4%. On Appointments, 96.5% against 98.2%. On Medicare, 34.8% against 25.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Phonic v1 starts replying 1.28s sooner at the median. Gemini 3.1 Flash Live Preview takes 2.88s at the median and 4.00s at p90; Phonic v1 takes 1.60s and 1.88s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Gemini 3.1 Flash Live Preview, by 0.09 on a 0 to 5 scale. Gemini 3.1 Flash Live Preview scores 4.98 and Phonic v1 4.89 for how well the agent handled being talked over.
Phonic v1, by 3.3 points. The agent went silent for 10 seconds or more on 3.3% of Gemini 3.1 Flash Live Preview calls and 0.0% of Phonic v1 calls.
Gemini 3.1 Flash Live Preview is $0.070 cheaper a minute. Gemini 3.1 Flash Live Preview costs $0.070 a minute of call and Phonic v1 $0.140, at each vendor's published rates.
Cekura ran both as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and connection. A simulated caller worked through all 82 scenarios on live calls, three times each, 2,952 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.