Gemini 3.1 Flash Live Preview is ahead on reliability, success rate, data accuracy, stalled calls, interruption and cost, and Deepslate Opal on response time. The two tie on agent responses.
Last updated Methodology by Dileep Chagam
Pick Deepslate Opal for fast replies (0.61s sooner). Pick Gemini 3.1 Flash Live Preview for reliability across repeated calls (4.9 points higher), calls that pass every check (6.1 points higher), saving the caller's data correctly (6.7 points higher), fewer stalled calls (2.0 points lower), handling interruptions (0.02 higher) and lower cost ($0.042 cheaper). They are level on getting the agent's replies right.
Scenarios that passed on all three runs.
Gemini 3.1 Flash Live, 4.9 points higher
Calls that passed every check.
Gemini 3.1 Flash Live, 6.1 points higher
Calls where the agent's replies reached the expected outcome.
Level
Calls where everything the agent saved matched exactly.
Gemini 3.1 Flash Live, 6.7 points higher
Calls where the agent went silent for 10 seconds or more.
Gemini 3.1 Flash Live, 2.0 points lower
How well it handled being talked over, 0 to 5.
Gemini 3.1 Flash Live, 0.02 higher
Median time to start replying after the caller finishes.
Deepslate Opal, 0.61s sooner
One minute of call at the vendor's published rates.
Gemini 3.1 Flash Live, $0.042 cheaper
The small figure is the place among ranked models. The cascade is not ranked.
Deepslate Opal 2.27s, Gemini 3.1 Flash Live 2.88s at the median.
Gemini 3.1 Flash Live Preview is more reliable, by 4.9 points. Deepslate Opal passed 47 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 phone 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, data accuracy, stalled calls, interruption and cost, and Deepslate Opal on response time. The two tie on agent responses.
Gemini 3.1 Flash Live Preview, by 6.7 points. Deepslate Opal saved everything exactly right on 72.6% of the calls that save data, and Gemini 3.1 Flash Live Preview on 79.2%. On Appointments, 85.4% against 96.5%. On Medicare, 39.4% against 34.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
Yes. Deepslate Opal starts replying 0.61s sooner at the median. Deepslate Opal takes 2.27s at the median and 2.83s 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 0.02 on a 0 to 5 scale. Deepslate Opal scores 4.96 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 2.0 points. The agent went silent for 10 seconds or more on 5.3% of Deepslate Opal calls and 3.3% of Gemini 3.1 Flash Live Preview calls.
Gemini 3.1 Flash Live Preview is $0.042 cheaper a minute. Deepslate Opal costs $0.112 a minute of call and Gemini 3.1 Flash Live Preview $0.070, 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.
