GPT Realtime 2.1OpenAI
Wins 6 of 8- Reliability
- 79.3%
- Response time
- 1.94s
- Cost / min
- $0.085
GPT Realtime 2.1vsPhonic v1
Phonic v1Phonic
Wins 2 of 8- Reliability
- 68.3%
- Response time
- 1.60s
- Cost / min
- $0.140
GPT Realtime 2.1 is ahead on reliability, success rate, agent responses, data accuracy, interruption and cost, and Phonic v1 on calls where the agent went quiet and response time.
Last updated Methodology by Dileep Chagam
Who is better at what
GPT Realtime 2.1Phonic v1
- Reliability79.3%68.3%
- Success rate89.0%77.2%
- Agent responses99.2%98.0%
- Data accuracy92.0%77.4%
- Went quiet3.3%0.0%
- Interruption4.984.89
- Response time1.94s1.60s
- Cost / min$0.085$0.140
Results by call
Right every time, on booking and Medicare calls
Booking callsMedicare calls
- GPT Realtime 2.1
- Booking calls
- 86.4%
- Medicare calls
- 60.9%
- Gap
- 25.6 points
86%61%GPT Realtime 2.1 - Phonic v1
- Booking calls
- 93.2%
- Medicare calls
- 4.3%
- Gap
- 88.9 points
93%4%Phonic v1
GPT Realtime 2.1 vs Phonic v1 FAQ
Is GPT Realtime 2.1 or Phonic v1 more reliable?
GPT Realtime 2.1 is more reliable, by 11.0 points. GPT Realtime 2.1 passed 65 of 82 scenarios on all three runs, and Phonic v1 passed 56. A scenario only counts when every run of it passed.
GPT Realtime 2.1 is more reliable, by 11.0 points. GPT Realtime 2.1 passed 65 of 82 scenarios on all three runs, and Phonic v1 passed 56. A scenario only counts when every run of it passed.
For a voice agent, GPT Realtime 2.1, since it gets more scenarios right on every run. GPT Realtime 2.1 is ahead on reliability, success rate, agent responses, data accuracy, interruption and cost, and Phonic v1 on calls where the agent went quiet and response time.
GPT Realtime 2.1, by 14.6 points. GPT Realtime 2.1 saved everything exactly right on 92.0% of the calls that save data, and Phonic v1 on 77.4%. On Booking calls, 95.9% against 98.2%. On Medicare calls, 81.8% against 25.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. Phonic v1 starts replying 0.33s sooner at the median. GPT Realtime 2.1 takes 1.94s at the median and 2.46s at p90; Phonic v1 takes 1.60s and 1.88s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
GPT Realtime 2.1, by 0.09 on a 0 to 5 scale. GPT Realtime 2.1 scores 4.98 and Phonic v1 4.89 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.
GPT Realtime 2.1 is $0.055 cheaper a minute. GPT Realtime 2.1 costs $0.085 a minute of call and Phonic v1 $0.140, 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, 3,198 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.