Gemini 3.1 Flash Live Preview vs Cascade

Cascade is more reliable, by 20.7 points. Gemini 3.1 Flash Live Preview passed 51 of 82 scenarios on all three runs, and Cascade passed 68. A scenario only counts when every run of it passed.

On reliability, no: the cascade passes more scenarios on every run. Cascade is ahead on reliability, success rate, agent responses, data accuracy, calls where the agent went quiet and response time, and Gemini 3.1 Flash Live Preview on interruption. Both ran as the same agent, with the same prompt and tools.

Cascade, by 14.9 points. Gemini 3.1 Flash Live Preview saved everything exactly right on 79.2% of the calls that save data, and Cascade on 94.1%. On Booking calls, 96.5% against 98.8%. On Medicare calls, 34.8% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. Cascade starts replying 0.71s sooner at the median. Gemini 3.1 Flash Live Preview takes 2.88s at the median and 4.00s at p90; Cascade takes 2.17s and 2.51s. 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. Gemini 3.1 Flash Live Preview scores 4.98 and Cascade 4.96 for how well the agent handled being talked over.

Cascade, by 2.5 points. The agent went quiet for 10 seconds or more on 3.3% of Gemini 3.1 Flash Live Preview calls and 0.8% of Cascade calls.

There is no verified per-minute rate for Cascade, 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. The cascade runs the same agent for reference and is never ranked.