Amazon Nova 2 Sonic vs GPT Realtime 2.1

GPT Realtime 2.1 is more reliable, by 21.4 points. Amazon Nova 2 Sonic handled 8 of 70 real callers well on all three runs, and GPT Realtime 2.1 23. A caller only counts when every run of the call scored 80 or more.

For a voice agent, GPT Realtime 2.1, since it handles more real callers well on every run. GPT Realtime 2.1 is ahead on ELO rating, hearing score, speaking score, task handling score, reliability, calls handled well, calls fully resolved and median latency, and Amazon Nova 2 Sonic on calls where the agent went quiet. The two tie on turn taking score.

GPT Realtime 2.1, by 20.5 points higher. Amazon Nova 2 Sonic fully resolved 13.8% of calls and GPT Realtime 2.1 34.3%. A call counts only when every step the caller needed was done.

No. GPT Realtime 2.1 starts replying 0.60s sooner at the median. Amazon Nova 2 Sonic takes 2.76s at the median and 3.40s at p90; GPT Realtime 2.1 takes 2.16s and 2.70s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

Amazon Nova 2 Sonic, by 4.8 points. The agent went quiet for 10 seconds or more on 7.1% of Amazon Nova 2 Sonic calls and 11.9% of GPT Realtime 2.1 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 with the same prompt, tools and phone connection. Both took the same 70 recorded real human callers on live calls, three times each. Each call is graded on 25 skills across Hearing, Turn Taking, Task Handling and Speaking, and passes at a score of 80 out of 100.