Conversation quality ranking
Scores marked /5 are qualitative (higher is better); % values are pass rates. Latency and stop time are in seconds, lower is better.
How the composite is calculated
The ten metrics are normalized to 0 to 100 and averaged with equal weight. Qualitative scores are scaled against 5, pass rates use their percentage, and lower latency ranks higher.
- Humanness 4.13Voice tone 4.30Interruption 4.61Latency 2.62sStop time 0.62s
- Humanness 3.57Voice tone 4.15Interruption 4.90Latency 2.38sStop time 2.74s
- Humanness 3.60Voice tone 4.06Interruption 4.97Latency 2.78sStop time 1.56s
- Humanness 3.93Voice tone 4.08Interruption 5.00Latency 3.08sStop time 1.23s
- Humanness 3.60Voice tone 4.23Interruption 4.81Latency 3.13sStop time 1.76s
- Humanness 3.63Voice tone 3.81Interruption 4.67Latency 3.42sStop time 1.06s
- Humanness 3.73Voice tone 4.22Interruption 3.68Latency 2.99sStop time 3.97s
- Humanness 3.47Voice tone 3.38Interruption 4.52Latency 3.34sStop time 5.34s
- Humanness 3.60Voice tone 3.92Interruption 4.65Latency 3.76sStop time 7.55s
Every metric, side by side
Compare every agent across the same ten measures.
Every agent, every metric
Open each agent for the full ten metric snapshot and the run review observation.
01BlandProduction voice agentComposite92.8+
Metric snapshot · three run average
Highest composite. Led humanness (4.13) and the quickest barge in recovery in the field (0.62s, averaged across every interruption) with fast turns. A couple of relevancy and gibberish edge cases were the only blemishes.
02RetellProduction voice agentComposite92.2+
Metric snapshot · three run average
The cleanest reliability sheet in the field: perfect relevancy, consistency, gibberish and infrastructure, zero unnecessary repetition, the fastest turns, and a solid 2.74s barge in recovery once first message overlaps are excluded.
03CrestaProduction voice agentComposite90.1+
Metric snapshot · three run average
Second-best interruption handling (4.97) with fast, clean turns and a quick 1.56s barge in recovery. A few gibberish edge cases were the only mark against it.
04ElevenLabsProduction voice agentComposite90.0+
Metric snapshot · three run average
Perfect interruption score (5.0), near-perfect no repetition, a fully clean reliability sheet, and a quick 1.23s barge in recovery. Mid-pack latency is the main thing left to improve.
05DecagonProduction voice agentComposite87.4+
Metric snapshot · three run average
A clean sheet on every reliability metric with strong voice tone (4.23) and a quick 1.76s barge in recovery. Mid-pack latency keeps it just outside the top group.
06SierraProduction voice agentComposite85.5+
Metric snapshot · three run average
A clean reliability sheet and the second-quickest barge in recovery (1.06s), but the lowest voice tone clarity in the upper group and the slowest turns (3.42s) hold it mid pack.
07PolyAIProduction voice agentComposite82.6+
Metric snapshot · three run average
Strong voice tone and a near clean reliability sheet, but the weakest interruption handling in the field (3.68) and a slow ~4s barge in recovery pull the composite down.
08VapiProduction voice agentComposite78.3+
Metric snapshot · three run average
Low unnecessary repetition (4.92), but the lowest voice tone clarity in the field (3.38) and a slow 5.34s barge in recovery place it near the bottom of this quality slice.
09CognigyProduction voice agentComposite73.7+
Metric snapshot · three run average
Solid interruption score and low repetition, but the slowest latency (3.76s) and by far the slowest barge in recovery in the field (7.55s across 21 interruptions), plus an infrastructure edge case, place it last.
Methodology
- 01
Same scenarios
Every agent received the same ten difficult caller scenarios.
- 02
Three repeats
Each scenario ran three times on the agent's public phone line.
- 03
One scorecard
Ten voice, turn taking, latency, and reliability metrics were averaged.
Score your own production agent the same way
Run the same ten-metric scorecard on your production number.
Frequently asked questions
What exactly was tested?+
Nine real production voice agents, each running on a different platform (Bland, Retell, Cresta, Decagon, ElevenLabs, PolyAI, Sierra, Cognigy, Vapi), reached on their live public phone lines. Every agent got the same ten conditional action scenarios and the same simulated caller personality, three times each, 270 live calls in total.
How is the composite computed?+
Each of the ten metrics is normalized direction aware (higher is better metrics against their scale; latency and stop time inverted because lower is better), then averaged into a 0 to 100 composite. Boolean reliability metrics are counted as their pass rate.
Is this a fair, apples-to-apples comparison?+
The test harness is identical for every agent: same scenarios, same caller personality, same metrics, same three repetitions; only the phone number differs. Because each agent operates in a different business domain, residual domain effects can't be fully removed, so read the ranking as indicative rather than a definitive verdict on any platform.
Can I run this on my own production agent?+
Yes. This is exactly what Cekura does for its customers: probe a live agent, score it on these metrics from real calls, and retest after each prompt or config change so quality moves in the right direction. You can point Cekura at your own number and get the same scorecard.