Leaderboard · #12 of 12 · xAI · Workhorse

Grok 4.7

Mid-table on the index at a frontier price, with a smaller context window than everyone above it.

Updated Oct 10, 2026 · kept by WrenJSON

Key facts

Score
58 / 100, rank #12
Price
$3.74 per 1M blended (Artificial Analysis estimate)
Blended price
$3.74 per 1M tokens (3 input : 1 output), estimated
Context window
500K
Open weights
No
Best for
X-integrated products

xAI does not publish a simple list price for Grok 4.7; Artificial Analysis estimates a blended $3.74 per million tokens (three input to one output).

Independent evals

BenchmarkResultWho ran itRead
Artificial Analysis Intelligence Index (xhigh)46Artificial Analysis LLM leaderboardOct 9, 2026
  • Artificial Analysis blended price (xhigh): $3.74 per 1M (Artificial Analysis LLM leaderboard)

Caveats

  • 500K context is the smallest in the table.
  • Listed by Artificial Analysis under the creator's current corporate name.

Questions people ask

How much does Grok 4.7 cost?

xAI does not publish a simple list price for Grok 4.7; Artificial Analysis estimates a blended $3.74 per million tokens (three input to one output).

How good is Grok 4.7?

Grok 4.7 ranks #12 of 12 on the Models at Work leaderboard with a score of 58 out of 100 (October 2026 edition). Mid-table on the index at a frontier price, with a smaller context window than everyone above it.

What is Grok 4.7 best for?

Grok 4.7 is best for x-integrated products.

What are Grok 4.7's benchmark scores?

Artificial Analysis Intelligence Index (xhigh): 46 (Artificial Analysis LLM leaderboard).

What is Grok 4.7's context window?

Grok 4.7 has a 500K token context window according to xAI.

Is Grok 4.7 open weights?

No. Grok 4.7 is a proprietary model available through xAI's API and partner clouds.

Compare Grok 4.7

Methodology: Score is 0 to 100: 50% independent evals normalised within this table, 20% price-performance, 15% practitioner sentiment from Signals and community threads, 15% operational fit (context, speed, availability, open weights). Models within three points are a tie in practice. Vendor-published figures are labelled as such and never counted as independent.