- Reliability (Pass³)
- 37.1%
- Latency P50
- 1.86s
- Cost per Minute (USD)
- $0.080
Gemini 3.1 Flash Live Preview is ahead on ELO rating, hearing score, turn taking score, speaking score, calls handled well and cost, and Azure Realtime on task handling score, reliability, calls fully resolved, calls where the agent went quiet and median latency.
Last updated Methodology by Dileep Chagam
Right every time, on booking and Healthcare calls
Each model on its own: Azure Realtime and Gemini 3.1 Flash Live Preview
Azure Realtime is more reliable, by 2.9 points. Azure Realtime handled 26 of 70 real callers well on all three runs, and Gemini 3.1 Flash Live Preview 24. A caller only counts when every run of the call scored 80 or more.
Azure Realtime is more reliable, by 2.9 points. Azure Realtime handled 26 of 70 real callers well on all three runs, and Gemini 3.1 Flash Live Preview 24. 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. Gemini 3.1 Flash Live Preview is ahead on ELO rating, hearing score, turn taking score, speaking score, calls handled well and cost, and Azure Realtime on task handling score, reliability, calls fully resolved, calls where the agent went quiet and median latency.
Azure Realtime, by 1.0 points higher. Azure Realtime fully resolved 25.7% of calls and Gemini 3.1 Flash Live Preview 24.8%. A call counts only when every step the caller needed was done.
Yes. Azure Realtime starts replying 1.20s sooner at the median. Azure Realtime takes 1.86s at the median and 2.10s at p90; Gemini 3.1 Flash Live Preview takes 3.06s and 3.86s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Azure Realtime, by 1.4 points. The agent went quiet for 10 seconds or more on 6.2% of Azure Realtime calls and 7.6% of Gemini 3.1 Flash Live Preview calls.
Gemini 3.1 Flash Live Preview is $0.009 cheaper a minute. Azure Realtime costs $0.080 a minute of call and Gemini 3.1 Flash Live Preview $0.070, 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.
Cekura runs these simulated calls on your agent and scores every one.