CekuraBench
All comparisons
GoogleOpenAI

Gemini 3.8 Live Extended Thinking 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 and response time, and Gemini 3.8 Live Extended Thinking 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 3.8 Live Thinking
56.1%6th
GPT-Live 1 + Sol low
75.6%2nd

GPT-Live 1 + Sol low, 19.5 points higher

Success rate

Calls that passed every check.

Gemini 3.8 Live Thinking
76.4%3rd
GPT-Live 1 + Sol low
83.7%2nd

GPT-Live 1 + Sol low, 7.3 points higher

Agent responses

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

Gemini 3.8 Live Thinking
94.7%6th
GPT-Live 1 + Sol low
100.0%1st

GPT-Live 1 + Sol low, 5.3 points higher

Data accuracy

Calls where everything the agent saved matched exactly.

Gemini 3.8 Live Thinking
80.2%3rd
GPT-Live 1 + Sol low
89.0%2nd

GPT-Live 1 + Sol low, 8.9 points higher

Stalled calls

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

Gemini 3.8 Live Thinking
3.7%6th
GPT-Live 1 + Sol low
12.2%8th

Gemini 3.8 Live Thinking, 8.5 points lower

Interruption

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

Gemini 3.8 Live Thinking
4.906th
GPT-Live 1 + Sol low
4.897th

Gemini 3.8 Live Thinking, 0.01 higher

Response time

Median time to start replying after the caller finishes.

Gemini 3.8 Live Thinking
2.32s7th
GPT-Live 1 + Sol low
2.02s4th

GPT-Live 1 + Sol low, 0.30s sooner

Cost / min

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

Gemini 3.8 Live Thinking
No verified rate
GPT-Live 1 + Sol low
$0.0552nd

Not comparable

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 3.8 Live Thinking 2.32s 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 3.8 Live Extended Thinking

  • Strong on the long form; when it slips, it skips a save it said it made.
  • Weak on the short form: phone numbers saved wrong, lookups never made.
  • Acts on half an answer instead of asking; weakest when the caller corrects themselves.
  • Least predictable: the same scenario passes one run and fails the next.
  • Replies fall behind or stop; callers hang up waiting.
Model
gemini-3.8-live-extended-thinking
Setting
Thinking level high
Voice
Charon
Turn taking
Shared local turn detection
Audio
16 kHz
Cost
Some calls used cached input the vendor meters at a rate we have not verified.

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 3.8 Live Extended Thinking or GPT-Live 1 + GPT-6 Sol (low thinking) more reliable?

Gemini 3.8 Live Extended Thinking passed 46 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 19.5 points.

Which saves caller data more accurately, Gemini 3.8 Live Extended Thinking or GPT-Live 1 + GPT-6 Sol (low thinking)?

Gemini 3.8 Live Extended Thinking saved everything exactly right on 80.2% of the calls that save data, and GPT-Live 1 + GPT-6 Sol (low thinking) on 89.0%. On Appointments, 86.5% against 100.0%. On Medicare, 63.6% against 60.6%. A call counts only when nothing is missing, wrong, extra or saved twice.

Which responds faster, Gemini 3.8 Live Extended Thinking or GPT-Live 1 + GPT-6 Sol (low thinking)?

GPT-Live 1 + GPT-6 Sol (low thinking) starts replying 0.30s sooner at the median. Gemini 3.8 Live Extended Thinking takes 2.32s at the median and 3.06s 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 3.8 Live Extended Thinking or GPT-Live 1 + GPT-6 Sol (low thinking)?

There is no verified per-minute rate for Gemini 3.8 Live Extended Thinking, so cost cannot be compared yet.

How were Gemini 3.8 Live Extended Thinking 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.