CekuraBench
All comparisons
GoogleOpenAI

Gemini 3.1 Flash Live Preview vs GPT-Live 1 + GPT-6 Sol (low thinking)

GPT-Live 1 + GPT-6 Sol (low thinking) is ahead on reliability, success rate, agent responses, data accuracy, response time and cost, and Gemini 3.1 Flash Live Preview on stalled calls and interruption.

Compare

Success rate by suite

Appointments59 scenariosMedicare23 scenarios
  • GPT Realtime 2.1OpenAI
    92%
    81%
  • GPT-Live 1 + Sol lowOpenAI
    97%
    49%
  • Gemini 3.8 Live ThinkingGoogle
    82%
    61%
  • Grok Think Fast 2.0xAI
    96%
    25%
  • Gemini 3.1 Flash LiveGoogle
    93%
    32%
  • Phonic v1Phonic
    97%
    14%
  • Realtime 2.1 MiniOpenAI
    84%
    4%
  • Nova 2 SonicAmazon
    80%
    6%
  • Cascade, GPT-4.1Not ranked
    97%
    83%
Each model's share of calls that passed every check, on each suite.

Every metric, side by side

Reliability

Scenarios that passed on all three runs.

Gemini 3.1 Flash Live
62.2%5th
GPT-Live 1 + Sol low
75.6%2nd

GPT-Live 1 + Sol low, 13.4 points higher

Success rate

Calls that passed every check.

Gemini 3.1 Flash Live
76.0%4th
GPT-Live 1 + Sol low
83.7%2nd

GPT-Live 1 + Sol low, 7.7 points higher

Agent responses

Calls where the agent's replies reached the expected outcome.

Gemini 3.1 Flash Live
95.9%5th
GPT-Live 1 + Sol low
100.0%1st

GPT-Live 1 + Sol low, 4.1 points higher

Data accuracy

Calls where everything the agent saved matched exactly.

Gemini 3.1 Flash Live
79.2%4th
GPT-Live 1 + Sol low
89.0%2nd

GPT-Live 1 + Sol low, 9.8 points higher

Stalled calls

Calls where the agent went silent for 10 seconds or more.

Gemini 3.1 Flash Live
3.3%5th
GPT-Live 1 + Sol low
12.2%8th

Gemini 3.1 Flash Live, 8.9 points lower

Interruption

How well it handled being talked over, 0 to 5.

Gemini 3.1 Flash Live
4.984th
GPT-Live 1 + Sol low
4.897th

Gemini 3.1 Flash Live, 0.09 higher

Response time

Median time to start replying after the caller finishes.

Gemini 3.1 Flash Live
2.88s8th
GPT-Live 1 + Sol low
2.02s4th

GPT-Live 1 + Sol low, 0.86s sooner

Cost / min

One minute of call at the vendor's published rates.

Gemini 3.1 Flash Live
$0.0703rd
GPT-Live 1 + Sol low
$0.0552nd

GPT-Live 1 + Sol low, $0.015 cheaper

The small figure is the place among ranked models. The cascade is not ranked.

GPT-Live 1 + Sol low answers first

GPT-Live 1 + Sol low 2.02s, Gemini 3.1 Flash Live 2.88s at the median.

Response time, median to p90

MedianTo p90
Medianp90
  • Phonic v1Phonic
    Phonic v1: median 1.59s, p90 1.86s
    1.59s1.86s
  • Grok Think Fast 2.0xAI
    Grok Think Fast 2.0: median 1.62s, p90 1.94s
    1.62s1.94s
  • GPT Realtime 2.1OpenAI
    GPT Realtime 2.1: median 1.94s, p90 2.46s
    1.94s2.46s
  • GPT-Live 1 + Sol lowOpenAI
    GPT-Live 1 + Sol low: median 2.02s, p90 2.42s
    2.02s2.42s
  • Realtime 2.1 MiniOpenAI
    Realtime 2.1 Mini: median 2.08s, p90 2.75s
    2.08s2.75s
  • Nova 2 SonicAmazon
    Nova 2 Sonic: median 2.18s, p90 2.76s
    2.18s2.76s
  • Gemini 3.8 Live ThinkingGoogle
    Gemini 3.8 Live Thinking: median 2.32s, p90 3.06s
    2.32s3.06s
  • Gemini 3.1 Flash LiveGoogle
    Gemini 3.1 Flash Live: median 2.88s, p90 4.00s
    2.88s4.00s
  • Cascade, GPT-4.1Not ranked
    Cascade, GPT-4.1: median 2.17s, p90 2.51s
    2.17s2.51s
2.0s3.0s4.0s
Seconds from the caller finishing to the agent starting to reply, per model.

What we saw on the calls

Gemini 3.1 Flash Live Preview

  • Steady on the short form, though it repeats lookups it already made.
  • On the long form it hands the caller over with the wrong details.
  • Slowest to reply; after several tool calls its replies fall behind or go missing.
  • Sometimes says goodbye without hanging up.
Model
models/gemini-3.1-flash-live-preview
Setting
Thinking level high
Voice
Charon
Turn taking
Shared local turn detection
Audio
16 kHz
Cost
Averaged over the calls with a usage record.

GPT-Live 1 + GPT-6 Sol (low thinking)

  • Near perfect on the short form, run after run.
  • Every failure is in the saved record; the conversation itself always reaches the outcome.
  • On the long form it routes the caller wrong or skips a step.
  • Says goodbye without hanging up, and stalls more than any other model.
  • Lowest voice score of the field.
Model
gpt-live-1
Setting
Delegates reasoning and tools to Sol
Voice
marin
Turn taking
Service turn detection
Audio
24 kHz
Cost
Includes the delegated backend model.
See the full leaderboardReference agent

Related comparisons

Frequently asked questions

Is Gemini 3.1 Flash Live Preview or GPT-Live 1 + GPT-6 Sol (low thinking) more reliable?

Gemini 3.1 Flash Live Preview passed 51 of 82 scenarios on all three runs, and GPT-Live 1 + GPT-6 Sol (low thinking) passed 62. GPT-Live 1 + GPT-6 Sol (low thinking) is ahead, by 13.4 points.

Which saves caller data more accurately, Gemini 3.1 Flash Live Preview or GPT-Live 1 + GPT-6 Sol (low thinking)?

Gemini 3.1 Flash Live Preview saved everything exactly right on 79.2% of the calls that save data, and GPT-Live 1 + GPT-6 Sol (low thinking) on 89.0%. On Appointments, 96.5% against 100.0%. On Medicare, 34.8% against 60.6%. A call counts only when nothing is missing, wrong, extra or saved twice.

Which responds faster, Gemini 3.1 Flash Live Preview or GPT-Live 1 + GPT-6 Sol (low thinking)?

GPT-Live 1 + GPT-6 Sol (low thinking) starts replying 0.86s sooner at the median. Gemini 3.1 Flash Live Preview takes 2.88s at the median and 4.00s at p90; GPT-Live 1 + GPT-6 Sol (low thinking) takes 2.02s and 2.42s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

Which costs less, Gemini 3.1 Flash Live Preview or GPT-Live 1 + GPT-6 Sol (low thinking)?

Gemini 3.1 Flash Live Preview costs $0.070 a minute of call and GPT-Live 1 + GPT-6 Sol (low thinking) $0.055, at each vendor's published rates. GPT-Live 1 + GPT-6 Sol (low thinking) is $0.015 cheaper a minute.

How were Gemini 3.1 Flash Live Preview and GPT-Live 1 + GPT-6 Sol (low thinking) compared?

Both ran as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and phone line. A simulated caller worked through all 82 scenarios on live calls, three times each, 2,214 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.