Verified, then logged.
Sun 22 Nov 2026 · 00:19 KST / 15:19 UTC한국어 | ENSearch /

Breaking01 / AI

OpenAI says GPT-6 Astra leads Retell's voice agent benchmark

The introduction to OpenAI's case study cites one benchmark as evidence and gives no sample size or evaluation conditions

A headset and desk speakerphone are wired to an audio analyzer on a bench in a foam-lined acoustic booth, with empty call-center desks and an out-of-focus technician seen from behind through the open door. AI-generated image

OpenAI reported in a case study published on 28 Oct 2026 that GPT-6 Astra leads Retell's voice agent benchmark, with no independent replication presented.

The introduction to the post names one basis for that ranking: Retell's benchmark, a performance comparison test of voice agents, which are AI systems that hold spoken conversations.

The post's title says OpenAI models help power 100M calls at Retell (monthly, company-reported).

OpenAI claimed that Codex has helped Retell reach an annual revenue run rate, a projection of yearly revenue from current sales, of $1.6M per employee (company-reported).

OpenAI's introduction does not report the benchmark's sample size or evaluation conditions, and no independent replication of the result has been presented.