GPT Realtime 2.1 is ahead on reliability, success rate, agent responses, data accuracy and response time, and Amazon Nova 2 Sonic on stalled calls and interruption.
Scenarios that passed on all three runs.
GPT Realtime 2.1, 29.3 points higher
Calls that passed every check.
GPT Realtime 2.1, 29.7 points higher
Calls where the agent's replies reached the expected outcome.
GPT Realtime 2.1, 5.3 points higher
Calls where everything the agent saved matched exactly.
GPT Realtime 2.1, 32.1 points higher
Calls where the agent went silent for 10 seconds or more.
Nova 2 Sonic, 2.0 points lower
How well it handled being talked over, 0 to 5.
Nova 2 Sonic, 0.01 higher
Median time to start replying after the caller finishes.
GPT Realtime 2.1, 0.25s 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, Nova 2 Sonic 2.18s at the median.
Amazon Nova 2 Sonic passed 41 of 82 scenarios on all three runs, and GPT Realtime 2.1 passed 65. GPT Realtime 2.1 is ahead, by 29.3 points.
Amazon Nova 2 Sonic saved everything exactly right on 59.9% of the calls that save data, and GPT Realtime 2.1 on 92.0%. On Appointments, 82.5% against 95.9%. On Medicare, 1.5% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
GPT Realtime 2.1 starts replying 0.25s sooner at the median. Amazon Nova 2 Sonic takes 2.18s at the median and 2.76s 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.
There is no verified per-minute rate for Amazon Nova 2 Sonic, so cost cannot be compared yet.
Both ran as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and phone line. A simulated caller worked through all 82 scenarios on live calls, three times each, 2,214 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
