Gemini 3.8 Live vs Rime Prism

Rime Prism is more reliable, by 26.8 points. Gemini 3.8 Live passed 34 of 82 scenarios on all three runs, and Rime Prism passed 56. A scenario only counts when every run of it passed.

For a voice agent, Rime Prism, since it gets more scenarios right on every run. Rime Prism is ahead on reliability, success rate, data accuracy, calls where the agent went quiet and response time, and Gemini 3.8 Live on agent responses and interruption.

Rime Prism, by 14.0 points. Gemini 3.8 Live saved everything exactly right on 70.5% of the calls that save data, and Rime Prism on 84.5%. On Booking calls, 78.4% against 92.4%. On Medicare calls, 50.0% against 64.2%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. Rime Prism starts replying 0.57s sooner at the median. Gemini 3.8 Live takes 1.91s at the median and 2.23s at p90; Rime Prism takes 1.34s and 1.57s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

Gemini 3.8 Live, by 0.07 on a 0 to 5 scale. Gemini 3.8 Live scores 4.98 and Rime Prism 4.91 for how well the agent handled being talked over.

Rime Prism, by 2.0 points. The agent went quiet for 10 seconds or more on 2.0% of Gemini 3.8 Live calls and 0.0% of Rime Prism calls.

There is no verified per-minute rate for Gemini 3.8 Live and Rime Prism, 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, 3,690 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.