GPT-6 Sol Max vs Grok 4.7 Xhigh: which scores higher?

GPT-6 Sol Max leads the intelligence index 44.2 to 35.5. Grok 4.7 Xhigh costs 25% less on blended price. Compare price, speed, latency and a clear verdict.

Metric	GPT-6 Sol (Max)	Grok 4.7 (Xhigh)
Intelligence Index	44.2	35.5
Input price (per 1M tokens)	$2.00	$2.00
Output price (per 1M tokens)	$10.00	$6.00
Output speed (tokens/s)	127	65
Time to first token	91s	43s
Release date	2026-09-22	2026-09-21

Metric

GPT-6 Sol (Max)

Grok 4.7 (Xhigh)

Intelligence Index

44.2

35.5

Input price (per 1M tokens)

$2.00

Output price (per 1M tokens)

$10.00

$6.00

Output speed (tokens/s)

127

Time to first token

91s

43s

Release date

2026-09-22

2026-09-21

GPT-6 Sol (Max) (OpenAI) and Grok 4.7 (Xhigh) (SpaceXAI) meet here on their recorded benchmark, price and speed data. No hands-on testing went into this write-up; it summarises the recorded benchmark, price and speed data for both models. The biggest separation is in overall capability: 44.2 for GPT-6 Sol Max against 35.5 for Grok 4.7 Xhigh.

Overall capability: 8.7 points apart

GPT-6 Sol Max comes out ahead on the intelligence index, 44.2 to 35.5. A difference this size usually separates one tier of model from the next. In relative terms, GPT-6 Sol Max scores 25% higher.

Among 109 active scored models, GPT-6 Sol Max sits 26th and Grok 4.7 Xhigh 38th.

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

When they came out

The release dates are September 21, 2026 for Grok 4.7 Xhigh and September 22, 2026 for GPT-6 Sol Max, one day apart. They are effectively contemporaries.

Running costs

Per million tokens, GPT-6 Sol Max charges $2.00 for input and $10.00 for output, while Grok 4.7 Xhigh charges $2.00 and $6.00. For output tokens, GPT-6 Sol Max is 1.7 times the price of Grok 4.7 Xhigh.

A reference job of 1 million input tokens and 200,000 output tokens costs $4.00 with GPT-6 Sol Max and $3.20 with Grok 4.7 Xhigh, so Grok 4.7 Xhigh saves $0.80. A bigger example, summarising 1,000 documents of 8,000 tokens into 400-token summaries, costs $20.00 on GPT-6 Sol Max and $18.40 on Grok 4.7 Xhigh: a gap of $1.60. Blended at three input tokens per output token, the effective rates are $4.00 for GPT-6 Sol Max and $3.00 for Grok 4.7 Xhigh.

Score per dollar

Dividing the blended price by the intelligence index gives a rough cost per point: $0.090 for GPT-6 Sol Max and $0.085 for Grok 4.7 Xhigh, per million tokens. On that measure they are priced in proportion to their scores.

GPT-6 Sol Max is the faster writer

GPT-6 Sol Max generates about 127 tokens per second and Grok 4.7 Xhigh about 65 tokens per second. That makes GPT-6 Sol Max roughly twice as fast at writing. Before any text appears, GPT-6 Sol Max takes 91 seconds and Grok 4.7 Xhigh 43 seconds. Short replies favour Grok 4.7 Xhigh; beyond about 6,400 tokens, GPT-6 Sol Max claws the time back. A first-token wait of that length suits background work better than live conversation.

Put together, a 1,000-token answer would take about 99 seconds from GPT-6 Sol Max and 59 seconds from Grok 4.7 Xhigh, counting the first-token wait.

Quick answers

Is GPT-6 Sol Max better than Grok 4.7 Xhigh?

Not across the board: GPT-6 Sol Max scores higher on the intelligence index, 44.2 to 35.5; Grok 4.7 Xhigh is 25% cheaper on blended price; GPT-6 Sol Max streams output twice as fast; and Grok 4.7 Xhigh reaches its first token sooner.

Is Grok 4.7 Xhigh cheaper than GPT-6 Sol Max?

Grok 4.7 Xhigh is cheaper on a blended basis. GPT-6 Sol Max lists $2.00 per million input tokens and $10.00 per million output tokens; Grok 4.7 Xhigh lists $2.00 and $6.00. For 1 million input and 200,000 output tokens that is $4.00 against $3.20.

Which model has lower latency?

GPT-6 Sol Max generates output faster, at 127 tokens per second against 65 tokens per second. Grok 4.7 Xhigh reaches its first token sooner (43 seconds against 91 seconds). Counting the first-token wait, Grok 4.7 Xhigh finishes short replies first and GPT-6 Sol Max pulls ahead beyond about 6,400 tokens.

Are GPT-6 Sol Max and Grok 4.7 Xhigh from the same company?

GPT-6 Sol Max is made by OpenAI and Grok 4.7 Xhigh by SpaceXAI. GPT-6 Sol Max was released on September 22, 2026 and Grok 4.7 Xhigh on September 21, 2026.

When were GPT-6 Sol Max and Grok 4.7 Xhigh released?

GPT-6 Sol Max is newer. It was released on September 22, 2026, one day after Grok 4.7 Xhigh (September 21, 2026).

Final whistle

In one line: on balance the numbers favour GPT-6 Sol Max, though Grok 4.7 Xhigh keeps a case of its own. Pick GPT-6 Sol Max if you need the higher overall score (44.2 against 35.5) and your outputs often run past about 6,400 tokens. Pick Grok 4.7 Xhigh if users are waiting on the first word and cost matters ($6.00 against $10.00 per million output tokens).

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the GPT-6 Sol (Max) and Grok 4.7 (Xhigh) pages. The AI Benchmark methodology explains how that data is collected and shown.