Amazon Nova 2 Sonic vs GPT Realtime 2.1 Mini

They are level on reliability. Amazon Nova 2 Sonic passed 41 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.

Reliability does not separate them, so pick on the metric your calls need most. GPT Realtime 2.1 Mini is ahead on success rate, data accuracy and response time, and Amazon Nova 2 Sonic on agent responses and calls where the agent went quiet. The two tie on reliability and interruption.

GPT Realtime 2.1 Mini, by 4.6 points. Amazon Nova 2 Sonic saved everything exactly right on 59.9% of the calls that save data, and GPT Realtime 2.1 Mini on 64.5%. On Booking calls, 82.5% against 88.8%. On Medicare calls, 1.5% against 0.0%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. GPT Realtime 2.1 Mini starts replying 0.10s sooner at the median. Amazon Nova 2 Sonic takes 2.18s at the median and 2.76s 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.

They score the same. Amazon Nova 2 Sonic scores 4.99 and GPT Realtime 2.1 Mini 4.99 for how well the agent handled being talked over.

Amazon Nova 2 Sonic, by 1.2 points. The agent went quiet for 10 seconds or more on 1.2% of Amazon Nova 2 Sonic calls and 2.5% of GPT Realtime 2.1 Mini calls.

There is no verified per-minute rate for Amazon Nova 2 Sonic, 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.