Grok Voice Think Fast 2.0 is ahead on reliability, success rate, agent responses, data accuracy and response time, and Gemini 3.8 Live on stalled calls and interruption.
Last updated Methodology by Dileep Chagam
Pick Gemini 3.8 Live for fewer stalled calls (2.4 points lower) and handling interruptions (0.06 higher). Pick Grok Voice Think Fast 2.0 for reliability across repeated calls (25.6 points higher), calls that pass every check (6.9 points higher), getting the agent's replies right (2.4 points higher), saving the caller's data correctly (8.4 points higher) and fast replies (0.28s sooner).
Scenarios that passed on all three runs.
Grok Think Fast 2.0, 25.6 points higher
Calls that passed every check.
Grok Think Fast 2.0, 6.9 points higher
Calls where the agent's replies reached the expected outcome.
Grok Think Fast 2.0, 2.4 points higher
Calls where everything the agent saved matched exactly.
Grok Think Fast 2.0, 8.4 points higher
Calls where the agent went silent for 10 seconds or more.
Gemini 3.8 Live, 2.4 points lower
How well it handled being talked over, 0 to 5.
Gemini 3.8 Live, 0.06 higher
Median time to start replying after the caller finishes.
Grok Think Fast 2.0, 0.28s 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.
Grok Think Fast 2.0 1.62s, Gemini 3.8 Live 1.91s at the median.
Grok Voice Think Fast 2.0 is more reliable, by 25.6 points. Gemini 3.8 Live passed 34 of 82 scenarios on all three runs, and Grok Voice Think Fast 2.0 passed 55. A scenario only counts when every run of it passed.
For a phone agent, Grok Voice Think Fast 2.0, since it gets more scenarios right on every run. Grok Voice Think Fast 2.0 is ahead on reliability, success rate, agent responses, data accuracy and response time, and Gemini 3.8 Live on stalled calls and interruption.
Grok Voice Think Fast 2.0, by 8.4 points. Gemini 3.8 Live saved everything exactly right on 70.5% of the calls that save data, and Grok Voice Think Fast 2.0 on 78.9%. On Appointments, 78.4% against 97.1%. On Medicare, 50.0% against 31.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Grok Voice Think Fast 2.0 starts replying 0.28s sooner at the median. Gemini 3.8 Live takes 1.91s at the median and 2.23s at p90; Grok Voice Think Fast 2.0 takes 1.62s and 1.94s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Gemini 3.8 Live, by 0.06 on a 0 to 5 scale. Gemini 3.8 Live scores 4.98 and Grok Voice Think Fast 2.0 4.92 for how well the agent handled being talked over.
Gemini 3.8 Live, by 2.4 points. The agent went silent for 10 seconds or more on 2.0% of Gemini 3.8 Live calls and 4.5% of Grok Voice Think Fast 2.0 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.
