CekuraBench

Phonic v1

Every modelCompare

68.3%

Reliability

5th of 12

1.60s

Median reply

2nd of 12

$0.140

Cost / min

9th of 9

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.

Phonic v1 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 Phonic v1 struggled

Phonic v1 falls furthest behind on Medicare compliance and routing: 28% passed, against a median of 40%.

Below the medianPassedMedian
  • Medicare compliance & routing
    28%median 40%
  • Safety & scope
    78%median 83%
  • Interruptions & barge-in
    87%median 90%

Response time at P50, P90 and P95

Phonic v1 starts replying in 1.60s on a typical turn and 1.96s on the slowest turn in twenty, 2nd 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.

Phonic v1 head to head

Every comparisonAll 12 models

How much audio Phonic v1 was tested on

246 live calls: 82 scenarios, each run three times. The median call ran 1:58.

Live calls
246
Scenarios
82
Booking calls
177
Medicare calls
69
Replies per call
7.3
Median call
1:58

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

Phonic v1 FAQ

  • Phonic v1 passed 56 of 82 scenarios on all three runs, 68.3%, 5th of 12 realtime models. Across all 246 calls, 77.2% passed every check.

  • Phonic v1 starts replying 1.60s after the caller finishes at the median, 1.88s at P90 and 1.96s at P95. That is 2nd fastest of 12 at the median, measured on the call audio.

  • Phonic v1 falls furthest behind the field on Medicare compliance and routing: 28% of calls passed, against a median of 40%.

  • Phonic v1 saved everything exactly right on 77.4% of the calls that save data, 8th of 12. On Booking calls, 98.2%. On Medicare calls, 25.0%.

  • $0.140 a minute of call at Phonic's published rates, 9th cheapest of 9 priced models. The vendor's Starter plan rate per conversation minute, applied to each call's length; the Pro plan is $0.12.

  • Cekura ran Phonic v1 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 Phonic v1. A call passes only when the agent said the right things and saved the right data.