Gemini 3.8 Live is ahead on agent responses, stalled calls, interruption and response time, and Gemini 3.8 Live Extended Thinking on reliability, success rate and data accuracy.
Last updated Methodology by Dileep Chagam
Pick Gemini 3.8 Live Extended Thinking for reliability across repeated calls (11.0 points higher), calls that pass every check (6.9 points higher) and saving the caller's data correctly (13.9 points higher). Pick Gemini 3.8 Live for getting the agent's replies right (5.7 points higher), fewer stalled calls (3.3 points lower), handling interruptions (0.03 higher) and fast replies (0.16s sooner).
Scenarios that passed on all three runs.
Gemini 3.8 Live Thinking, 11.0 points higher
Calls that passed every check.
Gemini 3.8 Live Thinking, 6.9 points higher
Calls where the agent's replies reached the expected outcome.
Gemini 3.8 Live, 5.7 points higher
Calls where everything the agent saved matched exactly.
Gemini 3.8 Live Thinking, 13.9 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, 0.03 higher
Median time to start replying after the caller finishes.
Gemini 3.8 Live, 0.16s 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, Gemini 3.8 Live Thinking 2.07s at the median.
Gemini 3.8 Live Extended Thinking is more reliable, by 11.0 points. Gemini 3.8 Live Extended Thinking passed 43 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, Gemini 3.8 Live Extended Thinking, since it gets more scenarios right on every run. Gemini 3.8 Live is ahead on agent responses, stalled calls, interruption and response time, and Gemini 3.8 Live Extended Thinking on reliability, success rate and data accuracy.
Gemini 3.8 Live Extended Thinking, by 13.9 points. Gemini 3.8 Live Extended Thinking saved everything exactly right on 84.4% of the calls that save data, and Gemini 3.8 Live on 70.5%. On Appointments, 88.9% against 78.4%. On Medicare, 72.7% against 50.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Gemini 3.8 Live starts replying 0.16s sooner at the median. Gemini 3.8 Live Extended Thinking takes 2.07s at the median and 2.74s 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 0.03 on a 0 to 5 scale. Gemini 3.8 Live Extended Thinking scores 4.95 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 Gemini 3.8 Live Extended Thinking calls and 2.0% of Gemini 3.8 Live calls.
There is no verified per-minute rate for Gemini 3.8 Live Extended Thinking and 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.
