Grok 4.6 Xhigh vs Grok 4.7 Xhigh: which scores higher?

Two SpaceXAI models meet here: Grok 4.6 (Xhigh) and Grok 4.7 (Xhigh). Grok 4.7 Xhigh leads the intelligence index 35.5 to 31.0, a gap of 4.5 points. What follows is built entirely from tracked data, so where the catalogue is silent, this page says so instead of guessing.

Reasoning and overall scores

Grok 4.7 Xhigh comes out ahead on the intelligence index, 35.5 to 31.0. A lead of this size is hard to dismiss as noise.

Among 109 active scored models, Grok 4.6 Xhigh sits 49th and Grok 4.7 Xhigh 38th.

The catalogue does not yet split either model's score into coding and math indexes.

Throughput and time to first token

Measured output speed is 62 tokens per second for Grok 4.6 Xhigh and 65 tokens per second for Grok 4.7 Xhigh. There is little to choose between them on raw output speed. Time to first token is 47 seconds for Grok 4.6 Xhigh and 43 seconds for Grok 4.7 Xhigh. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

Add the two numbers up for a 1,000-token reply and Grok 4.7 Xhigh finishes first: 63 seconds for Grok 4.6 Xhigh, 59 seconds for Grok 4.7 Xhigh.

Identical price sheets

The list prices are $2.00 in and $6.00 out for Grok 4.6 Xhigh, and $2.00 in and $6.00 out for Grok 4.7 Xhigh, per million tokens. With matching rates, cost drops out of the decision.

Which is newer

Grok 4.6 Xhigh came first, on August 12, 2026; Grok 4.7 Xhigh followed on September 21, 2026. They are effectively contemporaries.

Cost per point of intelligence

A blunt value measure, blended price over intelligence score, puts Grok 4.6 Xhigh at $0.097 and Grok 4.7 Xhigh at $0.085 per point. With the higher score and the lower cost per point, Grok 4.7 Xhigh is the better value per point on these numbers.