- Reliability
- 58.5%
- Response time
- 2.31s
- Cost / min
- $0.0224
Gemini 3.1 Flash Live Preview is ahead on reliability, success rate, agent responses, data accuracy, calls where the agent went quiet and interruption, and Deepslate Opal on response time and cost.
Last updated Methodology by Dileep Chagam
For the wider field, see our pick of the best voice AI APIs for real-time audio.
Scenarios the agent passed on every one of its 3 runs.
Each model on its own: Deepslate Opal and Gemini 3.1 Flash Live Preview
Gemini 3.1 Flash Live Preview is more reliable, by 3.7 points. Deepslate Opal passed 48 of 82 scenarios on all three runs, and Gemini 3.1 Flash Live Preview passed 51. A scenario only counts when every run of it passed.
Gemini 3.1 Flash Live Preview is more reliable, by 3.7 points. Deepslate Opal passed 48 of 82 scenarios on all three runs, and Gemini 3.1 Flash Live Preview passed 51. A scenario only counts when every run of it passed.
For a voice agent, Gemini 3.1 Flash Live Preview, since it gets more scenarios right on every run. Gemini 3.1 Flash Live Preview is ahead on reliability, success rate, agent responses, data accuracy, calls where the agent went quiet and interruption, and Deepslate Opal on response time and cost.
Gemini 3.1 Flash Live Preview, by 0.8 points. Deepslate Opal saved everything exactly right on 78.5% of the calls that save data, and Gemini 3.1 Flash Live Preview on 79.2%. On Booking calls, 88.3% against 96.5%. On Medicare calls, 53.0% against 34.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
Yes. Deepslate Opal starts replying 0.57s sooner at the median. Deepslate Opal takes 2.31s at the median and 2.88s at p90; Gemini 3.1 Flash Live Preview takes 2.88s and 4.00s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Gemini 3.1 Flash Live Preview, by 0.04 on a 0 to 5 scale. Deepslate Opal scores 4.94 and Gemini 3.1 Flash Live Preview 4.98 for how well the agent handled being talked over.
Gemini 3.1 Flash Live Preview, by 2.8 points. The agent went quiet for 10 seconds or more on 6.1% of Deepslate Opal calls and 3.3% of Gemini 3.1 Flash Live Preview calls.
Deepslate Opal is $0.0479 cheaper a minute. Deepslate Opal costs $0.0224 a minute of call and Gemini 3.1 Flash Live Preview $0.0703, 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, 3,936 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
Cekura runs these simulated calls on your agent and scores every one.