Artificial Analysis
2 stories · first 15 Oct · latest 2 Nov
Facts we checked
Each fact was checked against the page it links to.
-
Artificial Analysis's leaderboard, read on 2 November 2026, shows Gemini 4 Carbon (high) first with an Intelligence Index score of 59, Artificial Analysis's own measure.
LLM Leaderboard - Artificial Analysis · Artificial Analysis · archived copy · checked 2 Nov 2026 · Cite this fact · the story
-
SpaceXSI says Artificial Analysis measured an average cost per task on its Big Bench Audio run of $0.025 for Grok Voice 3.0, $0.030 for GPT-Live-1 (Astra, Medium) and $0.055 for GPT-Realtime-2.1 (High).
Introducing Grok Voice 3.0 · SpaceXSI (xAI) · archived copy · checked 15 Oct 2026 · Cite this fact · the story
-
SpaceXSI says Artificial Analysis's independent testing ranks Grok Voice 3.0 first on its Speech-to-Speech Index with a score of 86.9, against 83.2 for GPT-Live-1 (Astra, Medium) and 82.6 for Gemini 3.8 Live (Ext. Thinking, High), per a table dated 13 October 2026.
Introducing Grok Voice 3.0 · SpaceXSI (xAI) · archived copy · checked 15 Oct 2026 · Cite this fact · the story
All 2 stories
Cases
Its own pages
Pages the company published that our stories cite.
- LLM Leaderboard - Artificial Analysis · artificialanalysis.ai
Built from our published stories and the facts we checked, and kept up to date by them. How we correct.