GPT Realtime 2.1 vs Phonic v1

Phonic v1 is more reliable, by 11.0 points. GPT Realtime 2.1 passed 65 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 GPT Realtime 2.1 on agent responses and interruption.

Phonic v1, by 5.5 points. GPT Realtime 2.1 saved everything exactly right on 92.0% of the calls that save data, and Phonic v1 on 97.5%. On Booking calls, 95.9% against 100.0%. On Medicare calls, 81.8% against 90.9%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. Phonic v1 starts replying 0.30s sooner at the median. GPT Realtime 2.1 takes 1.94s at the median and 2.46s 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.

GPT Realtime 2.1, by 0.10 on a 0 to 5 scale. GPT Realtime 2.1 scores 4.98 and Phonic v1 4.88 for how well the agent handled being talked over.

Phonic v1, by 3.3 points. The agent went quiet for 10 seconds or more on 3.3% of GPT Realtime 2.1 calls and 0.0% of Phonic v1 calls.

Phonic v1 is $0.0253 cheaper a minute. GPT Realtime 2.1 costs $0.0853 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, 3,690 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.