Azure Realtime is ahead on reliability, success rate, agent responses, data accuracy, stalled calls and interruption, and Grok Voice Think Fast 2.0 on response time. The two tie on cost.
Last updated Methodology by Dileep Chagam
Pick Azure Realtime for reliability across repeated calls (3.7 points higher), calls that pass every check (8.1 points higher), getting the agent's replies right (2.0 points higher), saving the caller's data correctly (7.2 points higher), fewer stalled calls (0.4 points lower) and handling interruptions (0.04 higher). Pick Grok Voice Think Fast 2.0 for fast replies (0.03s sooner). They are level on lower cost.
Scenarios that passed on all three runs.
Azure Realtime, 3.7 points higher
Calls that passed every check.
Azure Realtime, 8.1 points higher
Calls where the agent's replies reached the expected outcome.
Azure Realtime, 2.0 points higher
Calls where everything the agent saved matched exactly.
Azure Realtime, 7.2 points higher
Calls where the agent went silent for 10 seconds or more.
Azure Realtime, 0.4 points lower
How well it handled being talked over, 0 to 5.
Azure Realtime, 0.04 higher
Median time to start replying after the caller finishes.
Grok Think Fast 2.0, 0.03s sooner
One minute of call at the vendor's published rates.
Level
The small figure is the place among ranked models. The cascade is not ranked.
Grok Think Fast 2.0 1.62s, Azure Realtime 1.66s at the median.
Azure Realtime is more reliable, by 3.7 points. Azure Realtime passed 58 of 82 scenarios on all three runs, and Grok Voice Think Fast 2.0 passed 55. A scenario only counts when every run of it passed.
For a phone agent, Azure Realtime, since it gets more scenarios right on every run. Azure Realtime is ahead on reliability, success rate, agent responses, data accuracy, stalled calls and interruption, and Grok Voice Think Fast 2.0 on response time. The two tie on cost.
Azure Realtime, by 7.2 points. Azure Realtime saved everything exactly right on 86.1% of the calls that save data, and Grok Voice Think Fast 2.0 on 78.9%. On Appointments, 94.2% against 97.1%. On Medicare, 65.2% against 31.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Grok Voice Think Fast 2.0 starts replying 0.03s sooner at the median. Azure Realtime takes 1.66s at the median and 2.22s at p90; Grok Voice Think Fast 2.0 takes 1.62s and 1.94s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Azure Realtime, by 0.04 on a 0 to 5 scale. Azure Realtime scores 4.96 and Grok Voice Think Fast 2.0 4.92 for how well the agent handled being talked over.
Azure Realtime, by 0.4 points. The agent went silent for 10 seconds or more on 4.1% of Azure Realtime calls and 4.5% of Grok Voice Think Fast 2.0 calls.
They cost the same. Azure Realtime costs $0.080 a minute of call and Grok Voice Think Fast 2.0 $0.080, 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, 2,952 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
