Azure Realtime vs GPT Realtime 2.1

Azure Realtime is more reliable, by 4.3 points. Azure Realtime handled 26 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, Azure Realtime, since it handles more real callers well on every run. GPT Realtime 2.1 is ahead on ELO rating, hearing score, turn taking score, speaking score, calls handled well and calls fully resolved, and Azure Realtime on reliability, calls where the agent went quiet, median latency and cost. The two tie on task handling score.

GPT Realtime 2.1, by 8.6 points higher. Azure Realtime fully resolved 25.7% of calls and GPT Realtime 2.1 34.3%. A call counts only when every step the caller needed was done.

Yes. Azure Realtime starts replying 0.30s sooner at the median. Azure Realtime takes 1.86s at the median and 2.10s 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.

Azure Realtime, by 5.7 points. The agent went quiet for 10 seconds or more on 6.2% of Azure Realtime calls and 11.9% of GPT Realtime 2.1 calls.

Azure Realtime is $0.006 cheaper a minute. Azure Realtime costs $0.080 a minute of call and GPT Realtime 2.1 $0.085, at each vendor's published rates.

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.