GPT-6.1 Terra Max vs Grok 4.7 Xhigh: benchmark scores compared

This matchup crosses tiers: GPT-6.1 Terra (Max) from OpenAI against Grok 4.7 (Xhigh) from SpaceXAI. Their widest difference is the intelligence index, with GPT-6.1 Terra Max ahead by 15.8 points (51.3 versus 35.5). No hands-on testing went into this write-up; it summarises the recorded benchmark, price and speed data for both models.

GPT-6.1 Terra Max leads on the intelligence index

On the intelligence index, GPT-6.1 Terra Max scores 51.3 against 35.5 for Grok 4.7 Xhigh. The difference is large enough that the lower-scoring model has to win on cost or speed to stay in the running. Put another way, Grok 4.7 Xhigh would need 45% more on this index to draw level.

Among 109 active scored models, GPT-6.1 Terra Max sits 14th and Grok 4.7 Xhigh 38th.

For coding or maths work specifically, the catalogue has no dedicated index on either side yet.

Running costs

The list prices are $1.00 in and $5.00 out for GPT-6.1 Terra Max, and $2.00 in and $6.00 out for Grok 4.7 Xhigh, per million tokens. For output tokens, Grok 4.7 Xhigh is 1.2 times the price of GPT-6.1 Terra Max.

Take 1 million input tokens and 200,000 output tokens: that comes to $2.00 on GPT-6.1 Terra Max and $3.20 on Grok 4.7 Xhigh. Scale it up to a month of coding-assistant traffic at 30 million input and 3 million output tokens and the bill is $45.00 for GPT-6.1 Terra Max against $78.00 for Grok 4.7 Xhigh.

Throughput and time to first token

GPT-6.1 Terra Max generates about 114 tokens per second and Grok 4.7 Xhigh about 65 tokens per second. That makes GPT-6.1 Terra Max roughly 1.8 times as fast at writing. Before any text appears, GPT-6.1 Terra Max takes 6.2 minutes and Grok 4.7 Xhigh 43 seconds. The faster writer, GPT-6.1 Terra Max, gives away too much at the start to win on time: counting the first-token wait, Grok 4.7 Xhigh finishes first for any reply shorter than about 49,000 tokens. A first-token wait of that length suits background work better than live conversation.

For a 1,000-token response, first token plus generation comes to roughly 6.3 minutes on GPT-6.1 Terra Max and 59 seconds on Grok 4.7 Xhigh.

Score per dollar

Dividing the blended price by the intelligence index gives a rough cost per point: $0.039 for GPT-6.1 Terra Max and $0.085 for Grok 4.7 Xhigh, per million tokens. GPT-6.1 Terra Max scores higher and costs less per point, so on price per point there is nothing to trade off.

When they came out

The release dates are September 21, 2026 for Grok 4.7 Xhigh and October 26, 2026 for GPT-6.1 Terra Max, 35 days apart. That is close enough to count them as the same generation.