Cekura Bench launches as first public Voice AI leaderboard, testing 50+ models on real calls
HeyToha · x · 2026-11-06
Cekura launched Cekura Bench, the first public Voice AI leaderboard testing 50+ models and platforms on identical real-world phone calls.
- 1000+ real caller scenarios; 5 open benchmarks spanning S2S, STT, TTS, and voice agent platforms
- Covers OpenAI, Google, Nvidia, xAI, ElevenLabs, Inworld, Vapi, Retell, LiveKit, Fish Audio and more
- Screenshot pass rates: Phonic1 leads at 90.2%, Grok Voice 3.0 at 81.7%, GPT Realtime 2.1 at 79.3%; Gemini 3.1 Flash Live Preview 62.2%, Amazon Nova 2 Sonic 50%
- Every recording, result and test case is public; models compared on naturalness, performance and cost
Voice AI previously relied on vendor demos — now there's a common yardstick.
Related event: Cekura Launches First Public Voice AI Benchmark Leaderboard(2 posts)→
More from Models
- A Claude names itself "Mythos" and genders itself in a rare first-person exchange — repligate · 2026-11-06
- SemiAnalysis: Google TPUv7 Delivers Up to 50% Better Performance-per-Dollar Than B200/B300 for Inference — vllm_project · 2026-11-06
- World Labs launches Frameboy: real-time exploration of Atlas world model at up to 15 fps — theworldlabs · 2026-11-06
- Nested meme of dev posting 'HIT THE WEEKLY LIMIT OF CLAUDE AGAIN' every month — m3nt3_ · 2026-11-06
- FrontierPhysics benchmark: Claude Opus 5.5 tops end-to-end physics research at 27.4% — xeophon · 2026-11-06
- Why AI writing feels annoying despite models winning literary competitions — cis_female · 2026-11-06