Cekura Bench
Strong signalSpeech-to-speech model benchmarks on live phone calls
Launched 23h ago
Signal
73
Velocity
0
What this means
30%Mid-tier finish likely.
Projecting attention of 125 by end of day-1.
24Founder Conviction Index: 24 — low signal.
Few of the conviction sub-signals (reputation, velocity, buyer-intent, tagline clarity) are firing yet.
Prediction
Top-5 finish probability
30%
today
Projected end-of-day votes
125range 94–169
Trajectory
stable
Vote pace holding steady.
About
Cekura Bench publishes voice AI benchmarks you can verify. Our new speech-to-speech benchmark tests 9 realtime voice models, including GPT Realtime 2.1, Gemini Live, Grok and Phonic, as complete phone agents on live calls: 82 scenarios, three runs each. Models are ranked on reliability, data accuracy, stalled calls, response time and cost, and every call transcript is public. Cekura Bench also covers voice agent benchmarks and STT benchmarks, with TTS benchmarks coming soon.
AI Summary
Cekura Bench provides verified benchmarks for speech-to-speech AI models tested on live phone calls, evaluating nine models across 82 scenarios. The platform ranks models based on reliability, data accuracy, response time, and cost, with all call transcripts publicly accessible.
Attention & discussion velocity
Performance
Velocity0
Vote pace vs average
Momentum16
Sustained over 6h
Virality0
Spread × engagement
Engagement25
Discussion per unit of attention
Editorial read
Scored deterministically. Only candidates that fire a story trigger are sent to a model, so this one has no written angle.
ThinLittle evidence and no strong angle. Nothing to build on yet.
125/8
Timeliness5%100
carried 7%
Trend20%30
carried 27%
Novelty15%30
carried 20%
Business15%21
carried 20%
Story20%0
carried 27%
Not measured · 3 of 8
Revenue10%—
Founder10%—
Cross-platform5%—
Gaps in our data, not findings about the product. Their weight is redistributed across the 5 we did measure.
measuredmeasured, zeronot measured
Full audit →Signal sources
3 of 6 active- Launch tracking4 readings since we picked it up
- AI analysisAI Agents
- Comment intelligencethread not yet analysed
- Outside discussionnot checked — domain is a storefront or shared
- Revenue signalsno match on this domain
- Editorial scoring23% evidence coverage
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.
