CekuraBench
Book a demo

Gemini 3.1 Flash Live Preview vs Gemini 3.8 Live Extended Thinking

All comparisonsLeaderboard
Compare
Gemini 3.1 Flash Live PreviewGoogle
Wins 4 of 8
Reliability
62.2%
Response time
2.88s
Cost / min
$0.0703
Gemini 3.8 Live Extended ThinkingGoogle
Wins 2 of 8
Reliability
52.4%
Response time
2.07s
Cost / min
n/a

Gemini 3.1 Flash Live Preview is ahead on reliability, agent responses, calls where the agent went quiet and interruption, and Gemini 3.8 Live Extended Thinking on data accuracy and response time. The two tie on success rate.

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 3.1 Flash Live PreviewGemini 3.8 Live Extended Thinking
  • Reliability62.2%52.4%
  • Success rate76.0%76.0%
  • Agent responses95.9%88.6%
  • Data accuracy79.2%84.4%
  • Went quiet3.3%5.3%
  • Interruption4.984.95
  • Response time2.88s2.07s
  • Cost / min$0.0703No verified rate

Reliability on booking and Medicare calls

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

Booking callsMedicare calls
  1. 59%
    35%
    Gemini 3.8 Live Extended Thinking
  2. 83%
    9%
    Gemini 3.1 Flash Live Preview

Related comparisons

Each model on its own: Gemini 3.1 Flash Live Preview and Gemini 3.8 Live Extended Thinking

Gemini 3.1 Flash Live Preview vs Gemini 3.8 Live Extended Thinking FAQ

  • Gemini 3.1 Flash Live Preview is more reliable, by 9.8 points. Gemini 3.1 Flash Live Preview passed 51 of 82 scenarios on all three runs, and Gemini 3.8 Live Extended Thinking passed 43. A scenario only counts when every run of it passed.

  • For a voice agent, Gemini 3.1 Flash Live Preview, since it gets more scenarios right on every run. Gemini 3.1 Flash Live Preview is ahead on reliability, agent responses, calls where the agent went quiet and interruption, and Gemini 3.8 Live Extended Thinking on data accuracy and response time. The two tie on success rate.

  • Gemini 3.8 Live Extended Thinking, by 5.2 points. Gemini 3.1 Flash Live Preview saved everything exactly right on 79.2% of the calls that save data, and Gemini 3.8 Live Extended Thinking on 84.4%. On Booking calls, 96.5% against 88.9%. On Medicare calls, 34.8% against 72.7%. A call counts only when nothing is missing, wrong, extra or saved twice.

  • No. Gemini 3.8 Live Extended Thinking starts replying 0.81s sooner at the median. Gemini 3.1 Flash Live Preview takes 2.88s at the median and 4.00s at p90; Gemini 3.8 Live Extended Thinking takes 2.07s and 2.74s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

  • Gemini 3.1 Flash Live Preview, by 0.03 on a 0 to 5 scale. Gemini 3.1 Flash Live Preview scores 4.98 and Gemini 3.8 Live Extended Thinking 4.95 for how well the agent handled being talked over.

  • Gemini 3.1 Flash Live Preview, by 2.0 points. The agent went quiet for 10 seconds or more on 3.3% of Gemini 3.1 Flash Live Preview calls and 5.3% of Gemini 3.8 Live Extended Thinking calls.

  • There is no verified per-minute rate for Gemini 3.8 Live Extended Thinking, 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, 3,690 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.

Book a demoStart free