Deepslate Opal is ahead on reliability, success rate, agent responses and data accuracy, and Gemini 3.8 Live on stalled calls, interruption and response time.
Last updated Methodology by Dileep Chagam
Pick Deepslate Opal for reliability across repeated calls (15.9 points higher), calls that pass every check (0.8 points higher), getting the agent's replies right (1.6 points higher) and saving the caller's data correctly (2.1 points higher). Pick Gemini 3.8 Live for fewer stalled calls (3.3 points lower), handling interruptions (0.02 higher) and fast replies (0.37s sooner).
Scenarios that passed on all three runs.
Deepslate Opal, 15.9 points higher
Calls that passed every check.
Deepslate Opal, 0.8 points higher
Calls where the agent's replies reached the expected outcome.
Deepslate Opal, 1.6 points higher
Calls where everything the agent saved matched exactly.
Deepslate Opal, 2.1 points higher
Calls where the agent went silent for 10 seconds or more.
Gemini 3.8 Live, 3.3 points lower
How well it handled being talked over, 0 to 5.
Gemini 3.8 Live, 0.02 higher
Median time to start replying after the caller finishes.
Gemini 3.8 Live, 0.37s sooner
One minute of call at the vendor's published rates.
Not comparable
The small figure is the place among ranked models. The cascade is not ranked.
Gemini 3.8 Live 1.91s, Deepslate Opal 2.27s at the median.
Deepslate Opal is more reliable, by 15.9 points. Deepslate Opal passed 47 of 82 scenarios on all three runs, and Gemini 3.8 Live passed 34. A scenario only counts when every run of it passed.
For a phone agent, Deepslate Opal, since it gets more scenarios right on every run. Deepslate Opal is ahead on reliability, success rate, agent responses and data accuracy, and Gemini 3.8 Live on stalled calls, interruption and response time.
Deepslate Opal, by 2.1 points. Deepslate Opal saved everything exactly right on 72.6% of the calls that save data, and Gemini 3.8 Live on 70.5%. On Appointments, 85.4% against 78.4%. On Medicare, 39.4% against 50.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Gemini 3.8 Live starts replying 0.37s sooner at the median. Deepslate Opal takes 2.27s at the median and 2.83s at p90; Gemini 3.8 Live takes 1.91s and 2.23s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Gemini 3.8 Live, by 0.02 on a 0 to 5 scale. Deepslate Opal scores 4.96 and Gemini 3.8 Live 4.98 for how well the agent handled being talked over.
Gemini 3.8 Live, by 3.3 points. The agent went silent for 10 seconds or more on 5.3% of Deepslate Opal calls and 2.0% of Gemini 3.8 Live calls.
There is no verified per-minute rate for Gemini 3.8 Live, so cost cannot be compared yet.
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.
