Gemini 3.8 Live vs GPT Realtime 2.1

Compare
Gemini 3.8 LiveGoogle
Wins 2 of 8
Reliability
41.5%
Response time
1.91s
Cost / min
n/a
GPT Realtime 2.1OpenAI
Wins 4 of 8
Reliability
79.3%
Response time
1.94s
Cost / min
$0.0853

GPT Realtime 2.1 is ahead on reliability, success rate, agent responses and data accuracy, and Gemini 3.8 Live on calls where the agent went quiet and response time. The two tie on interruption.

Last updated Methodology by Dileep Chagam

Who is better at what

For the wider field, see our pick of the best voice AI APIs for real-time audio.

Gemini 3.8 LiveGPT Realtime 2.1
  • Reliability41.5%79.3%
  • Success rate69.1%89.0%
  • Agent responses94.3%99.2%
  • Data accuracy70.5%92.0%
  • Went quiet2.0%3.3%
  • Interruption4.984.98
  • Response time1.91s1.94s
  • Cost / minNo verified rate$0.0853

Reliability on booking and Medicare calls

Scenarios the agent passed on every one of its 3 runs.

Booking callsMedicare calls
  1. 86%
    61%
    GPT Realtime 2.1
  2. 53%
    13%
    Gemini 3.8 Live

Gemini 3.8 Live vs GPT Realtime 2.1 FAQ

  • GPT Realtime 2.1 is more reliable, by 37.8 points. Gemini 3.8 Live passed 34 of 82 scenarios on all three runs, and GPT Realtime 2.1 passed 65. 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 and data accuracy, and Gemini 3.8 Live on calls where the agent went quiet and response time. The two tie on interruption.

  • GPT Realtime 2.1, by 21.5 points. Gemini 3.8 Live saved everything exactly right on 70.5% of the calls that save data, and GPT Realtime 2.1 on 92.0%. On Booking calls, 78.4% against 95.9%. On Medicare calls, 50.0% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.

  • Yes. Gemini 3.8 Live starts replying 0.03s sooner at the median. Gemini 3.8 Live takes 1.91s at the median and 2.23s at p90; GPT Realtime 2.1 takes 1.94s and 2.46s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

  • They score the same. Gemini 3.8 Live scores 4.98 and GPT Realtime 2.1 4.98 for how well the agent handled being talked over.

  • Gemini 3.8 Live, by 1.2 points. The agent went quiet for 10 seconds or more on 2.0% of Gemini 3.8 Live calls and 3.3% of GPT Realtime 2.1 calls.

  • There is no verified per-minute rate for Gemini 3.8 Live, 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, 3,936 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.