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

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.