Gemini 3.8 Live Extended Thinking vs GPT Realtime 2.1 Mini

Gemini 3.8 Live Extended Thinking is more reliable, by 2.4 points. Gemini 3.8 Live Extended Thinking passed 43 of 82 scenarios on all three runs, and GPT Realtime 2.1 Mini passed 41. A scenario only counts when every run of it passed.

For a voice agent, Gemini 3.8 Live Extended Thinking, since it gets more scenarios right on every run. Gemini 3.8 Live Extended Thinking is ahead on reliability, success rate, data accuracy and response time, and GPT Realtime 2.1 Mini on agent responses, calls where the agent went quiet and interruption.

Gemini 3.8 Live Extended Thinking, by 19.9 points. Gemini 3.8 Live Extended Thinking saved everything exactly right on 84.4% of the calls that save data, and GPT Realtime 2.1 Mini on 64.5%. On Booking calls, 88.9% against 88.8%. On Medicare calls, 72.7% against 0.0%. A call counts only when nothing is missing, wrong, extra or saved twice.

Yes. Gemini 3.8 Live Extended Thinking starts replying 0.01s sooner at the median. Gemini 3.8 Live Extended Thinking takes 2.07s at the median and 2.74s at p90; GPT Realtime 2.1 Mini takes 2.08s and 2.75s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

GPT Realtime 2.1 Mini, by 0.04 on a 0 to 5 scale. Gemini 3.8 Live Extended Thinking scores 4.95 and GPT Realtime 2.1 Mini 4.99 for how well the agent handled being talked over.

GPT Realtime 2.1 Mini, by 2.8 points. The agent went quiet for 10 seconds or more on 5.3% of Gemini 3.8 Live Extended Thinking calls and 2.5% of GPT Realtime 2.1 Mini calls.

There is no verified per-minute rate for Gemini 3.8 Live Extended Thinking, 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.