Skip to content
Yardstick
  1. Models
  2. SpaceXAI
  3. Grok 4.7

Grok 4.7

SpaceXAI · Flagship · Sep 21, 2026New

SpaceXAI's frontier model for coding, agents and knowledge work.

Announcement (opens in a new tab)
Artificial Analysis Intelligence Index
46.5#8 of 29 · xhigh effort
API price per 1M tokens
$2 / $6input / output · $3 blended
Context window
500Ktokens
Output speed
73 t/s74s to first answer at xhigh effort

Benchmark results

Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.

Overall capability

  • Artificial Analysis Intelligence Index46.5#8 of 29

    Xhigh effort

    11.357.6
  • Epoch Capabilities Index153.5#14 of 16
    146.9167.3
  • LiveBench77.4%#11 of 23

    Xhigh effort

    63.9%83.4%

Coding

  • Terminal-Bench 4.037.6%#8 of 13

    Grok Build harness, xhigh effort

    14.6%64.8%
  • Arena WebDev1,638#10 of 27

    Xhigh effort

    1,2631,814

Agents & professional work

  • GDPval-AA1,712#4 of 18

    Xhigh effort

    1,2421,866
  • Vending-Bench 2$10,537#3 of 9
    $2,158$15,515

Reasoning

  • ARC-AGI-261.4%#8 of 11

    Xhigh effort

    42.4%95%
  • ARC-AGI-31.8%#4 of 5

    Xhigh effort

    0.2%62.7%
  • FrontierMath (Tiers 1–3)53%#14 of 14

    Xhigh effort

    53%93.7%
  • MathArena46.7%#7 of 10

    Xhigh effort

    35.3%90.1%

Knowledge & science

  • Humanity's Last Exam (Diamond)23.4%#6 of 9
    13.4%60.6%
  • GPQA Diamond92.7%#7 of 14

    Xhigh effort

    90.2%95.8%

Human preference

  • Arena Text1,442#20 of 24

    Xhigh effort

    1,4251,525

Reasoning effort trade-offs

The same model at different thinking budgets. More effort buys a higher intelligence score at a higher cost per task and a longer wait. Measured by Artificial Analysis.

EffortScoreCost / taskFirst answerSpeed
Low
42.2
$1.255.1s69 t/s
High
46.3
$2.7387s79 t/s
Xhigh (headline score)
46.5
$3.7474s73 t/s

Specs & pricing

Developer
SpaceXAI
Released
Sep 21, 2026
Availability
Generally available
API model ID
grok-4.7
Weights
Proprietary (API only)
Reasoning
Adjustable effort
Knowledge cutoff
May 2026
Accepts
Text, Image
Produces
Text
Context window
500,000 tokens
Input price
$2 / 1M tokens
Output price
$6 / 1M tokens
Cached input
$0.50 / 1M tokens

Prompts of 200K tokens or more are billed at $4 input / $12 output per 1M tokens for the whole request.

Closest alternatives

Models from other labs nearest to Grok 4.7 on Artificial Analysis Intelligence Index.

  • MiMo-V2.6-Pro

    Xiaomi

    Intelligence 46.3 · $0.435 / $0.87

    Compare side by side

  • Qwen3.8-Max

    Alibaba

    Intelligence 45.4 · $2 / $6

    Compare side by side

  • Muse Spark 1.3

    Meta

    Intelligence 48.1 · $1.25 / $4.25

    Compare side by side

Sources

  • Announcement (opens in a new tab)
  • Model documentation (opens in a new tab)
  • Pricing (opens in a new tab)
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs