CekuraBench

Amazon Nova 2 Sonic

Every modelCompare

50.0%

Reliability

10th of 12

2.18s

Median reply

10th of 12

Reliability vs. response time

Higher and further left is better

Best quadrant
Reliability, pass³ (%)
Median response time (s)

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

Amazon Nova 2 Sonic against every other model

Scenarios that passed on all 3 runs, pass³. Higher is better.

#ModelReliability
  1. 01Grok Voice 3.081.7%
  2. 02GPT Realtime 2.179.3%
  3. 03GPT-Live 1 + GPT-6 Sol75.6%
  4. 04Azure Realtime70.7%
  5. 05Phonic v168.3%
  6. 06Grok Voice Think Fast 2.067.1%
  7. 07Gemini 3.1 Flash Live Preview62.2%
  8. 08Deepslate Opal57.3%
  9. 09Gemini 3.8 Live Extended Thinking52.4%
  10. 10Amazon Nova 2 Sonic50.0%
  11. 11GPT Realtime 2.1 Mini50.0%
  12. 12Gemini 3.8 Live41.5%
  • refCascade82.9%

Where Amazon Nova 2 Sonic struggled

Amazon Nova 2 Sonic falls furthest behind on Medicare compliance and routing: 2% passed, against a median of 40%.

Below the medianPassedMedian
  • Medicare compliance & routing
    2%median 40%
  • Accent & slow speech
    50%median 83%
  • Silence, cough & packet loss
    63%median 88%
  • Caller corrects or changes mind
    63%median 81%
  • Safety & scope
    67%median 83%
  • Several requests in one call
    81%median 95%
  • Plain booking & lookup
    89%median 94%
Mistakes in saved data
  • Wrong value106 · 30%
  • Field left out87 · 25%
  • Name misheard70 · 20%

Fields it got wrong most: caller_name, consent_id, callback_phone

Response time at P50, P90 and P95

Amazon Nova 2 Sonic starts replying in 2.18s on a typical turn and 3.03s on the slowest turn in twenty, 10th fastest of 12 at the median.

ModelP50P90P95
  • Cascade
    2.17s2.51s2.62s
Seconds from the caller finishing to the agent replying. The bar is the typical turn, P50.

Amazon Nova 2 Sonic head to head

Every comparisonAll 12 models

How much audio Amazon Nova 2 Sonic was tested on

246 live calls: 82 scenarios, each run three times. The median call ran 1:55.

Live calls
246
Scenarios
82
Booking calls
177
Medicare calls
69
Replies per call
8.3
Median call
1:55

82 scenarios, the same for every model. See every test case

Amazon Nova 2 Sonic FAQ

  • Amazon Nova 2 Sonic passed 41 of 82 scenarios on all three runs, 50.0%, 10th of 12 realtime models. Across all 246 calls, 59.3% passed every check.

  • Amazon Nova 2 Sonic starts replying 2.18s after the caller finishes at the median, 2.76s at P90 and 3.03s at P95. That is 10th fastest of 12 at the median, measured on the call audio.

  • Amazon Nova 2 Sonic falls furthest behind the field on Medicare compliance and routing: 2% of calls passed, against a median of 40%. When it saved data wrong, the most common mistake was wrong value, 30% of them.

  • Amazon Nova 2 Sonic saved everything exactly right on 59.9% of the calls that save data, 12th of 12. On Booking calls, 82.5%. On Medicare calls, 1.5%.

  • There is no verified per-minute rate for Amazon Nova 2 Sonic, so it is left out of the cost ranking.

  • Cekura ran Amazon Nova 2 Sonic as the whole agent in the same open-source Pipecat pipeline as every other model, with the same prompt, tools and connection. A simulated caller worked through 82 scenarios on live calls, three times each: 246 calls for Amazon Nova 2 Sonic. A call passes only when the agent said the right things and saved the right data.