Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d65, 14 pendingSources1,013

Grok 4.7

SpaceXAIReleased Sep 21, 2026Current

Score basis

Grok 4.7 is strong in factuality; capable in long context and reasoning; and behind the leaders in multimodal tasks, agentic tasks, coding, instruction following, and math. Too few results yet to rate safety or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Strong1 capability
  1. Factuality−5.6%3 of 4
Capable2 capabilities
  1. Long Context−16.7%1 of 3
  2. Reasoning−20.3%4 of 6
Limited5 capabilities
  1. Multimodal−26.4%1 of 6
  2. Agentic−27.4%2 of 7
  3. Coding−31.3%4 of 10
  4. Instruction Following−31.3%1 of 3
  5. Math−38.2%5 of 5
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$2.00input$6.00outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 75% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

65results on32benchmarks

  • 27 independently verified
  • 32 aggregator
  • 6 vendor-reported

From 10 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Grok 4.7 benchmark results

65 results on 32 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

StrongFull factuality ranking

5.6% behind the leader3 of 4 ranked benchmarks measured

Show 4 more factuality resultsHide 4 factuality results

Long Context

CapableFull long context ranking

16.7% behind the leader1 of 3 ranked benchmarks measured

Show 2 more long context resultsHide 2 long context results

Reasoning

CapableFull reasoning ranking

20.3% behind the leader4 of 6 ranked benchmarks measured

Show 15 more reasoning resultsHide 15 reasoning results

Multimodal

LimitedFull multimodal ranking

26.4% behind the leader1 of 6 ranked benchmarks measured

Agentic

LimitedFull agentic ranking

27.4% behind the leader2 of 7 ranked benchmarks measured

Show 5 more agentic resultsHide 5 agentic results

Coding

LimitedFull coding ranking

31.3% behind the leader4 of 10 ranked benchmarks measured

Show 2 more coding resultsHide 2 coding results

Instruction Following

LimitedFull instruction following ranking

31.3% behind the leader1 of 3 ranked benchmarks measured

Math

LimitedFull math ranking

38.2% behind the leader5 of 5 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 12 more resultsHide 12 results

Grok 4.7: common questions

Who makes Grok 4.7?

Grok 4.7 is made by SpaceXAI.

When was Grok 4.7 released?

Grok 4.7 was released on Sep 21, 2026, according to SpaceXAI's own announcement.

What is Grok 4.7 good at?

Grok 4.7 is strong in factuality; capable in long context and reasoning; and behind the leaders in multimodal tasks, agentic tasks, coding, instruction following, and math. Too few results yet to rate safety or multilingual tasks.

How much does Grok 4.7 cost?

Grok 4.7 costs $2.00 per million input tokens and $6.00 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 75% of the 331 priced models we track.

How many benchmarks has Grok 4.7 been tested on?

We track 65 results for Grok 4.7 on 32 benchmarks from 10 sources, 27 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Grok 4.7 support?

OpenRouter lists tool calling, structured outputs, and reasoning for Grok 4.7.

About this record

Where Grok 4.7's numbers come from, and every name it appears under.

Tracked since
Aug 6, 2026
Newest source mention
Oct 7, 2026

Where the results come from

Verification: 65 scores · 27 independently verified · 32 aggregator-attributed · 6 vendor-reported. How these tiers are assigned

From 10 sources on 6 sites. Artificial Analysis supplies 32 of them; the 27 independently verified results come from 4 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai32
  • arcprize.org16
  • livebench.ai7
  • api.llm-stats.com6
  • epoch.ai3
  • datasets-server.huggingface.co1

Also known as

How our sources name Grok 4.7 at each reasoning setting.

SettingShort formAPI id
lowgrok 4.7 (low)grok-4-7-low
mediumgrok 4.7 (medium)—
highgrok 4.7 (high)grok-4-7-high
xhighgrok 4.7 (xhigh)grok-4.7-xhigh
Also listed asgrok-4-7grock 4.7