Flux → GPT-4.1 → ElevenLabs Flash is ahead on reliability, success rate, agent responses, data accuracy and interruption, and Phonic v1 on stalled calls and response time.
Last updated Methodology by Dileep Chagam
Pick Phonic v1 for fewer stalled calls (0.8 points lower) and fast replies (0.57s sooner). Pick Flux → GPT-4.1 → ElevenLabs Flash for reliability across repeated calls (14.6 points higher), calls that pass every check (15.9 points higher), getting the agent's replies right (1.2 points higher), saving the caller's data correctly (16.7 points higher) and handling interruptions (0.07 higher).
Scenarios that passed on all three runs.
Cascade, GPT-4.1, 14.6 points higher
Calls that passed every check.
Cascade, GPT-4.1, 15.9 points higher
Calls where the agent's replies reached the expected outcome.
Cascade, GPT-4.1, 1.2 points higher
Calls where everything the agent saved matched exactly.
Cascade, GPT-4.1, 16.7 points higher
Calls where the agent went silent for 10 seconds or more.
Phonic v1, 0.8 points lower
How well it handled being talked over, 0 to 5.
Cascade, GPT-4.1, 0.07 higher
Median time to start replying after the caller finishes.
Phonic v1, 0.57s sooner
One minute of call at the vendor's published rates.
Not comparable
The small figure is the place among ranked models. The cascade is not ranked.
Phonic v1 1.60s, Cascade, GPT-4.1 2.17s at the median.
Flux → GPT-4.1 → ElevenLabs Flash is more reliable, by 14.6 points. Phonic v1 passed 56 of 82 scenarios on all three runs, and Flux → GPT-4.1 → ElevenLabs Flash passed 68. A scenario only counts when every run of it passed.
On reliability, no: the Flux → GPT-4.1 → ElevenLabs Flash cascade passes more scenarios on every run. Flux → GPT-4.1 → ElevenLabs Flash is ahead on reliability, success rate, agent responses, data accuracy and interruption, and Phonic v1 on stalled calls and response time. Both ran as the same agent, with the same prompt and tools.
Flux → GPT-4.1 → ElevenLabs Flash, by 16.7 points. Phonic v1 saved everything exactly right on 77.4% of the calls that save data, and Flux → GPT-4.1 → ElevenLabs Flash on 94.1%. On Appointments, 98.2% against 98.8%. On Medicare, 25.0% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.
Yes. Phonic v1 starts replying 0.57s sooner at the median. Phonic v1 takes 1.60s at the median and 1.88s at p90; Flux → GPT-4.1 → ElevenLabs Flash takes 2.17s and 2.51s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
Flux → GPT-4.1 → ElevenLabs Flash, by 0.07 on a 0 to 5 scale. Phonic v1 scores 4.89 and Flux → GPT-4.1 → ElevenLabs Flash 4.96 for how well the agent handled being talked over.
Phonic v1, by 0.8 points. The agent went silent for 10 seconds or more on 0.0% of Phonic v1 calls and 0.8% of Flux → GPT-4.1 → ElevenLabs Flash calls.
There is no verified per-minute rate for Flux → GPT-4.1 → ElevenLabs Flash, so cost cannot be compared yet.
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. The cascade runs the same agent for reference and is never ranked.
