Cekura Bench

Speech-to-speech model benchmarks on live phone calls

Upvote this launch

3 launch images

About this launch

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.

Discussion

0 comments

Questions, feedback, and notes from the community.

Join the conversation