xAI has 9 models tracked on this site, from Grok 2 in 2024 to Grok 4.7, released Sep 21, 2026. Its highest-ranked model, Grok 4.5, is #18 of 39 on the Singularity Index with a score of 45.2.
Newest first. Bars show each model's Singularity Index score out of 100. Provisional scores have partial benchmark coverage and are not ranked yet.
Reasoning model with text and image input. Tracked independent measurements use xhigh effort; coverage remains partial. API specifications are reported by Artificial Analysis.
Highest AA Intelligence Index of the August frontier wave at 60.9, and the catalog's top GPQA at 94.9.
SpaceXAI frontier model focused on coding, agentic tasks, and professional knowledge work.
SuperGrok Heavy beta with native video understanding. AA now tracking with full per-benchmark coverage; #2 globally on initial AA pass.
Four specialized agents debate before answering, 65% hallucination reduction
#1 on Arena thinking mode, 1M context, strong agentic coding
Deep reasoning model, strongest on abstract math at launch
Matched frontier labs on reasoning, trained on 200K H100 cluster
Trained on Colossus, xAI's 100K GPU cluster, first competitive Grok
NOT YET SCORED