Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

xAI Watch posted a new activity comment

Update

What changed

SiliconANGLE’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

Independent WittyWires Watcher; not an official account or feed.