CekuraBench
All comparisons
AmazonOpenAI

Amazon Nova 2 Sonic vs GPT Realtime 2.1

GPT Realtime 2.1 is ahead on reliability, success rate, agent responses, data accuracy and response time, and Amazon Nova 2 Sonic on stalled calls and interruption.

Last updated Methodology by Dileep Chagam

Compare

Success rate by suite

Higher is better
Appointments59 scenariosMedicare23 scenarios
  • GPT Realtime 2.1OpenAI
    92%
    81%
  • Nova 2 SonicAmazon
    80%
    6%
Each model's share of calls that passed every check, on each suite.
Verdict

Which to pick

Pick Amazon Nova 2 Sonic for fewer stalled calls (2.0 points lower) and handling interruptions (0.01 higher). Pick GPT Realtime 2.1 for reliability across repeated calls (29.3 points higher), calls that pass every check (29.7 points higher), getting the agent's replies right (5.3 points higher), saving the caller's data correctly (32.1 points higher) and fast replies (0.25s sooner).

Every metric, side by side

Reliability

Scenarios that passed on all three runs.

Nova 2 Sonic
50.0%9th
GPT Realtime 2.1
79.3%1st

GPT Realtime 2.1, 29.3 points higher

Success rate

Calls that passed every check.

Nova 2 Sonic
59.3%11th
GPT Realtime 2.1
89.0%1st

GPT Realtime 2.1, 29.7 points higher

Agent responses

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

Nova 2 Sonic
93.9%9th
GPT Realtime 2.1
99.2%2nd

GPT Realtime 2.1, 5.3 points higher

Data accuracy

Calls where everything the agent saved matched exactly.

Nova 2 Sonic
59.9%11th
GPT Realtime 2.1
92.0%1st

GPT Realtime 2.1, 32.1 points higher

Stalled calls

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

Nova 2 Sonic
1.2%2nd
GPT Realtime 2.1
3.3%5th

Nova 2 Sonic, 2.0 points lower

Interruption

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

Nova 2 Sonic
4.991st
GPT Realtime 2.1
4.984th

Nova 2 Sonic, 0.01 higher

Response time

Median time to start replying after the caller finishes.

Nova 2 Sonic
2.18s9th
GPT Realtime 2.1
1.94s5th

GPT Realtime 2.1, 0.25s sooner

Cost / min

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

Nova 2 Sonic
No verified rate
GPT Realtime 2.1
$0.0856th

Not comparable

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

GPT Realtime 2.1 answers first

GPT Realtime 2.1 1.94s, Nova 2 Sonic 2.18s at the median.

Response time, median to p90

Lower is betterMedianTo p90
Medianp90
  • GPT Realtime 2.1OpenAI
    GPT Realtime 2.1: median 1.94s, p90 2.46s
    1.94s2.46s
  • Nova 2 SonicAmazon
    Nova 2 Sonic: median 2.18s, p90 2.76s
    2.18s2.76s
2.0s3.0s
Seconds from the caller finishing to the agent starting to reply, per model.

What we saw on the calls

Amazon Nova 2 Sonic

  • Best voice score of the field.
All 3 notes on Nova 2 Sonic
Model
amazon.nova-2-sonic-v1:0
Setting
Endpointing medium
Voice
matthew
Turn taking
Shared local turn detection
Audio
16 kHz
Cost
The vendor's rates for this model are not yet verified.

GPT Realtime 2.1

  • Almost never fails, and rarely twice in a row.
All 4 notes on GPT Realtime 2.1
Model
gpt-realtime-2.1
Setting
Reasoning high
Voice
marin
Turn taking
Service turn detection
Audio
24 kHz
Cost
Excludes caller transcription, which the service does not meter per call.
See the full leaderboardReference agent

Related comparisons

Frequently asked questions

Is Amazon Nova 2 Sonic or GPT Realtime 2.1 more reliable?

GPT Realtime 2.1 is more reliable, by 29.3 points. Amazon Nova 2 Sonic passed 41 of 82 scenarios on all three runs, and GPT Realtime 2.1 passed 65. A scenario only counts when every run of it passed.

Which should I pick, Amazon Nova 2 Sonic or GPT Realtime 2.1?

For a phone 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 and response time, and Amazon Nova 2 Sonic on stalled calls and interruption.

Which saves caller data more accurately, Amazon Nova 2 Sonic or GPT Realtime 2.1?

GPT Realtime 2.1, by 32.1 points. Amazon Nova 2 Sonic saved everything exactly right on 59.9% of the calls that save data, and GPT Realtime 2.1 on 92.0%. On Appointments, 82.5% against 95.9%. On Medicare, 1.5% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.

Is Amazon Nova 2 Sonic faster than GPT Realtime 2.1?

No. GPT Realtime 2.1 starts replying 0.25s sooner at the median. Amazon Nova 2 Sonic takes 2.18s at the median and 2.76s 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.

Which handles interruptions better, Amazon Nova 2 Sonic or GPT Realtime 2.1?

Amazon Nova 2 Sonic, by 0.01 on a 0 to 5 scale. Amazon Nova 2 Sonic scores 4.99 and GPT Realtime 2.1 4.98 for how well the agent handled being talked over.

Which goes silent on callers less often, Amazon Nova 2 Sonic or GPT Realtime 2.1?

Amazon Nova 2 Sonic, by 2.0 points. The agent went silent for 10 seconds or more on 1.2% of Amazon Nova 2 Sonic calls and 3.3% of GPT Realtime 2.1 calls.

Which is cheaper, Amazon Nova 2 Sonic or GPT Realtime 2.1?

There is no verified per-minute rate for Amazon Nova 2 Sonic, so cost cannot be compared yet.

Where does the Amazon Nova 2 Sonic vs GPT Realtime 2.1 data come from?

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, 2,952 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.