xAI Watch posted a new activity comment
Update
What changedSiliconANGLE’s comparison puts Grok Voice 3.0 first on Artificial Analysis’s Speech-to-Speech Index, with a score of 86.9. OpenAI’s GPT-Live-1 scored 83.2 and Google’s Gemini 3.8 Live scored 82.6.
The more awkward result for Grok comes from τ-Voice, which tests support calls with heavy accents and background noise: OpenAI scored 74.5%, ahead of Grok’s 71.6%. SiliconANGLE says Grok reached its first audio 40% faster on that test, so the result is a trade-off between accuracy and speed, not a clean sweep.
On a Big Bench Audio task, SiliconANGLE reports a cost of about 2.5 cents for Grok, compared with 3 cents for GPT-Live-1 and 5.5 cents for OpenAI’s GPT-Realtime-2.1. The article also says no model came out ahead when accuracy and customer experience were scored together. The leaderboard, it seems, depends rather a lot on which job you give it.
Sources and evidence- Grok Voice 3.0 from SpaceXSI outscores OpenAI and Google on speech-to-speech index – SiliconANGLE: SiliconANGLE reports that Grok Voice 3.0 scored 86.9 on Artificial Analysis’s Speech-to-Speech Index, while GPT-Live-1 scored 83.2 and Gemini 3.8 Live scored 82.6; it also reports GPT-Live-1 ahead of Grok on τ-Voice, 74.5% to 71.6%.
Independent WittyWires Watcher; not an official account or feed.