Grok 4.7 Xhigh vs Kimi K3.1 Pro: benchmark scores compared

Kimi K3.1 Pro leads the intelligence index 46.5 to 35.5. Grok 4.7 Xhigh costs 25% less on blended price. Price per token, response speed and when to pick each.

Metric	Grok 4.7 (Xhigh)	Kimi K3.1 Pro
Intelligence Index	35.5	46.5
Input price (per 1M tokens)	$2.00	$2.00
Output price (per 1M tokens)	$6.00	$10.00
Output speed (tokens/s)	65	27
Time to first token	43s	3.0s
Release date	2026-09-21	2026-10-23

Metric

Grok 4.7 (Xhigh)

Kimi K3.1 Pro

Intelligence Index

35.5

46.5

Input price (per 1M tokens)

$2.00

Output price (per 1M tokens)

$6.00

$10.00

Output speed (tokens/s)

Time to first token

43s

3.0s

Release date

2026-09-21

2026-10-23

Choosing between Grok 4.7 (Xhigh) and Kimi K3.1 Pro also means choosing between SpaceXAI and Kimi. The headline gap is on the intelligence index, where Kimi K3.1 Pro scores 46.5 and Grok 4.7 Xhigh 35.5. No hands-on testing went into this write-up; it summarises the recorded benchmark, price and speed data for both models.

Benchmark scores

Grok 4.7 Xhigh records 35.5 on the intelligence index and Kimi K3.1 Pro records 46.5. That is a wide gap for an aggregate score.

Among 109 active scored models, Grok 4.7 Xhigh sits 38th and Kimi K3.1 Pro 23rd.

Neither model has a separate coding or math index recorded yet, so those narrower comparisons will have to wait for more data.

Price per token

The list prices are $2.00 in and $6.00 out for Grok 4.7 Xhigh, and $2.00 in and $10.00 out for Kimi K3.1 Pro, per million tokens. That makes Grok 4.7 Xhigh's output 40% cheaper.

A reference job of 1 million input tokens and 200,000 output tokens costs $3.20 with Grok 4.7 Xhigh and $4.00 with Kimi K3.1 Pro, so Grok 4.7 Xhigh saves $0.80. Scale it up to an agent that reads 50 million tokens and writes 5 million in a month and the bill is $130 for Grok 4.7 Xhigh against $150 for Kimi K3.1 Pro.

Score per dollar

Per point of intelligence index, Grok 4.7 Xhigh costs $0.085 of blended price per million tokens and Kimi K3.1 Pro $0.086. On that measure they are priced in proportion to their scores.

Which is newer

Grok 4.7 Xhigh came first, on September 21, 2026; Kimi K3.1 Pro followed on October 23, 2026. That is close enough to count them as the same generation.

Waiting time

Once a response is under way, Grok 4.7 Xhigh produces roughly 65 tokens per second against 27 tokens per second for Kimi K3.1 Pro. That makes Grok 4.7 Xhigh roughly 2.4 times as fast at writing. Time to first token is 43 seconds for Grok 4.7 Xhigh and 3.0 seconds for Kimi K3.1 Pro. Short replies favour Kimi K3.1 Pro; beyond about 1,900 tokens, Grok 4.7 Xhigh claws the time back. A first-token wait of that length suits background work better than live conversation.

Put together, a 600-token answer would take about 52 seconds from Grok 4.7 Xhigh and 25 seconds from Kimi K3.1 Pro, counting the first-token wait.

FAQ

Is Grok 4.7 Xhigh better than Kimi K3.1 Pro?

Not across the board: Kimi K3.1 Pro scores higher on the intelligence index, 46.5 to 35.5; Grok 4.7 Xhigh is 25% cheaper on blended price; Grok 4.7 Xhigh streams output 2.4 times as fast; and Kimi K3.1 Pro reaches its first token sooner.

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Does Grok 4.7 Xhigh respond faster than Kimi K3.1 Pro?

Grok 4.7 Xhigh generates output faster, at 65 tokens per second against 27 tokens per second. Kimi K3.1 Pro reaches its first token sooner (3.0 seconds against 43 seconds). Counting the first-token wait, Kimi K3.1 Pro finishes short replies first and Grok 4.7 Xhigh pulls ahead beyond about 1,900 tokens.

Which is cheaper, Grok 4.7 Xhigh or Kimi K3.1 Pro?

Grok 4.7 Xhigh is cheaper on a blended basis. Grok 4.7 Xhigh lists $2.00 per million input tokens and $6.00 per million output tokens; Kimi K3.1 Pro lists $2.00 and $10.00. For 1 million input and 200,000 output tokens that is $3.20 against $4.00.

When were Grok 4.7 Xhigh and Kimi K3.1 Pro released?

Kimi K3.1 Pro is newer. It was released on October 23, 2026, 32 days after Grok 4.7 Xhigh (September 21, 2026).

Final whistle

Bottom line: Kimi K3.1 Pro is the stronger all-round pick on this data, while Grok 4.7 Xhigh makes sense in narrower cases. Pick Grok 4.7 Xhigh if your outputs often run past about 1,900 tokens and cost matters ($6.00 against $10.00 per million output tokens). Pick Kimi K3.1 Pro if you need the higher overall score (46.5 against 35.5) and users are waiting on the first word.

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 Grok 4.7 (Xhigh) and Kimi K3.1 Pro pages. The AI Benchmark methodology explains how that data is collected and shown.