GPT Realtime 2.1 is ahead of Gemini 3.8 Live Extended Thinking on reliability, success rate, agent responses, data accuracy, stalled calls, interruption and response time.
Last updated Methodology by Dileep Chagam
GPT Realtime 2.1 is the better pick over Gemini 3.8 Live Extended Thinking on every measure that separates them: reliability across repeated calls (26.8 points higher), calls that pass every check (13.0 points higher), getting the agent's replies right (10.6 points higher), saving the caller's data correctly (7.6 points higher), fewer stalled calls (2.0 points lower), handling interruptions (0.03 higher) and fast replies (0.13s sooner).
Scenarios that passed on all three runs.
GPT Realtime 2.1, 26.8 points higher
Calls that passed every check.
GPT Realtime 2.1, 13.0 points higher
Calls where the agent's replies reached the expected outcome.
GPT Realtime 2.1, 10.6 points higher
Calls where everything the agent saved matched exactly.
GPT Realtime 2.1, 7.6 points higher
Calls where the agent went silent for 10 seconds or more.
GPT Realtime 2.1, 2.0 points lower
How well it handled being talked over, 0 to 5.
GPT Realtime 2.1, 0.03 higher
Median time to start replying after the caller finishes.
GPT Realtime 2.1, 0.13s 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.
GPT Realtime 2.1 1.94s, Gemini 3.8 Live Thinking 2.07s at the median.
Both providers, every model: Google vs OpenAI
GPT Realtime 2.1 is more reliable, by 26.8 points. Gemini 3.8 Live Extended Thinking passed 43 of 82 scenarios on all three runs, and GPT Realtime 2.1 passed 65. A scenario only counts when every run of it passed.
For a phone agent, GPT Realtime 2.1, since it gets more scenarios right on every run. GPT Realtime 2.1 is ahead of Gemini 3.8 Live Extended Thinking on reliability, success rate, agent responses, data accuracy, stalled calls, interruption and response time.
GPT Realtime 2.1, by 7.6 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 on 92.0%. On Appointments, 88.9% against 95.9%. On Medicare, 72.7% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. GPT Realtime 2.1 starts replying 0.13s 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 takes 1.94s and 2.46s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
GPT Realtime 2.1, by 0.03 on a 0 to 5 scale. Gemini 3.8 Live Extended Thinking scores 4.95 and GPT Realtime 2.1 4.98 for how well the agent handled being talked over.
GPT Realtime 2.1, by 2.0 points. The agent went silent for 10 seconds or more on 5.3% of Gemini 3.8 Live Extended Thinking calls and 3.3% of GPT Realtime 2.1 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, 2,952 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
