- Reliability
- 70.7%
- Response time
- 1.66s
- Cost / min
- $0.0798
Phonic v1 is ahead on reliability, success rate, data accuracy, calls where the agent went quiet, response time and cost, and Azure Realtime on agent responses and interruption.
Last updated Methodology by Dileep Chagam
Our guide covers testing OpenAI Realtime API voice agents.
Scenarios the agent passed on every one of its 3 runs.
Phonic v1 is more reliable, by 19.5 points. Azure Realtime passed 58 of 82 scenarios on all three runs, and Phonic v1 passed 74. A scenario only counts when every run of it passed.
Phonic v1 is more reliable, by 19.5 points. Azure Realtime passed 58 of 82 scenarios on all three runs, and Phonic v1 passed 74. A scenario only counts when every run of it passed.
For a voice agent, Phonic v1, since it gets more scenarios right on every run. Phonic v1 is ahead on reliability, success rate, data accuracy, calls where the agent went quiet, response time and cost, and Azure Realtime on agent responses and interruption.
Phonic v1, by 11.4 points. Azure Realtime saved everything exactly right on 86.1% of the calls that save data, and Phonic v1 on 97.5%. On Booking calls, 94.2% against 100.0%. On Medicare calls, 65.2% against 90.9%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Phonic v1 starts replying 0.02s sooner at the median. Azure Realtime takes 1.66s at the median and 2.22s at p90; Phonic v1 takes 1.63s and 1.81s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Azure Realtime, by 0.09 on a 0 to 5 scale. Azure Realtime scores 4.96 and Phonic v1 4.88 for how well the agent handled being talked over.
Phonic v1, by 4.1 points. The agent went quiet for 10 seconds or more on 4.1% of Azure Realtime calls and 0.0% of Phonic v1 calls.
Phonic v1 is $0.0198 cheaper a minute. Azure Realtime costs $0.0798 a minute of call and Phonic v1 $0.0600, at each vendor's published rates.
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, 3,936 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
Cekura runs these simulated calls on your agent and scores every one.