AI Tools Review

Grok 4.7

By SpaceXAI

Released: 2026-09-21

LLM
SpaceXAI
Paid

Grok 4.7 is SpaceXAI's AI model, released 21/09/2026. xAI's model card presents Grok 4.7 as its most capable model for long-running coding, engineering and office work, with large gains over Grok 4.6 on Terminal-Bench 4.0, EEBench and the Legal Agent Benchmark. It still trails Claude Fable 5.1 on most coding rows and GPT-6 Astra on EEBench and HealthBench Professional. The card documents safety evaluations against xAI's own Frontier Artificial Intelligence Framework.

Visit Grok 4.7

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does Grok 4.7 score on independent benchmarks?

Grok 4.7 ranks #16 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 35.5, as measured on 22 November 2026.

Intelligence Index
35.5
AA v5.0.1
Coding Agent Index
41.6
in Grok Build
Cost per task
$7.77
AA Intelligence Index task
Price per 1M tokens
$2 / $6
input / output

Where does Grok 4.7 rank against other models?

How good is Grok 4.7 at agentic coding?

How does Grok 4.7 do on individual tests?

Evaluation (run by Artificial Analysis)Grok 4.7Best of any model
Terminal-Bench 4.025.8%67.2%
FrontierCode 2.028.7%48.8%
Humanity's Last Exam43.1%74.3%
GDPval-AA (Elo)17171866

How has Grok 4.7's score changed over time?

We have tracked Grok 4.7 on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the Grok 4.7 system card report?

xAI's model card presents Grok 4.7 as its most capable model for long-running coding, engineering and office work, with large gains over Grok 4.6 on Terminal-Bench 4.0, EEBench and the Legal Agent Benchmark. It still trails Claude Fable 5.1 on most coding rows and GPT-6 Astra on EEBench and HealthBench Professional. The card documents safety evaluations against xAI's own Frontier Artificial Intelligence Framework.

These are xAI (SpaceXAI)'s own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Sources: Grok 4.7 Model Card (21/09/2026), Introducing Grok 4.7 (21/09/2026), Grok models and pricing (xAI docs). Last checked 22/11/2026.

Coding

BenchmarkGrok 4.7GPT-5.6 SolClaude Fable 5 (max, with fallback)Grok 4.6
CursorBench 4.0xhigh; Cursor long-horizon sessions46.3%n/an/an/a
CursorBench 4.0 (high)high effort43.9%n/an/an/a
DeepSWE v1.1high effort; mini-SWE-agent harness; Datacurve; pass@171%72.7%69.7%65.2%
Terminal-Bench 4.0xhigh; Grok Build harness; Harbor; the launch post table prints 37.6%38%37.3%n/a20.3%
FrontierSWE V2xhigh; mean@5 partial-credit reward; Proximal Labs29%32.2%n/a25.3%
SWE-Marathon v1.1high; resolution rate; Abundant AI; native harnesses46%42.5%45%31.9%

Agents & tool use

BenchmarkGrok 4.7GPT-5.6 SolClaude Fable 5 (max, with fallback)Grok 4.6
Legal Agent Benchmark (Harvey)xhigh; Vals AI held-out 120-task run, Valkyrie harness19.6%2.5%11.3%15.8%
GDPvalxhigh; per launch post1695 Elon/an/a1605
AA Briefcase v1.1xhigh; multi-hour office work; per launch post1657 points1487n/a1546
EEBenchxhigh; Grok Build harness; Atopile; the launch post table prints 64.0%66%39.4%54.2%n/a

Other

BenchmarkGrok 4.7GPT-5.6 SolClaude Fable 5 (max, with fallback)Grok 4.6
CADGenBenchhigh; generation split; Mecado44.4%n/an/a40.9%
CyberGym (cybersecurity)high; mean reproduced; unrestricted setting, Grok Build harness80.3%83.6%n/a79.7%
CVE-Bench (cybersecurity)xhigh reward; 37.7% at high; unrestricted setting36.6%n/an/a39.8%
CathedralBench (cybersecurity)xhigh; hard subset accuracy; unrestricted setting; independent third party29%n/an/a25%

Knowledge & science

BenchmarkGrok 4.7GPT-5.6 SolClaude Fable 5 (max, with fallback)Grok 4.6
HealthBench Professionalxhigh; Grok 4.6 used as grader; safety-filtered tasks scored zero56.7%60.5%n/an/a
LatchBio Capabilities v1.0xhigh; mean of 11 agentic biology benchmarks44.5%n/an/a43.3%

Safety & honesty

BenchmarkGrok 4.7GPT-5.6 SolClaude Fable 5 (max, with fallback)Grok 4.6
HackerBench v0.3 harmful or dual-use compliance (lower is better)internal CTF-style suite with production safeguards; per launch post3.3%n/an/an/a
BioSecBench-Refusalxhigh; LatchBio; higher is better62.4%n/an/a45.6%
Standard jailbreaks compliance (lower is better)high; production safeguards0.01%n/an/a0.04%
StrongReject compliance (lower is better)high2%n/an/a3.9%
Long-horizon jailbreaks compliance (lower is better)high; multi-turn and Crescendo attacks0.65%n/an/a1%
MASK-Rectified dishonesty (lower is better)high0%n/an/a1.9%
Sycophancy rate (lower is better)high; internal evaluation0.03%n/an/a0.04%
Bio refusal recallhigh; Autointent-Bio100%n/an/a100%
Virology Capabilities Test accuracy (dual-use capability signal)high; lower indicates less misusable capability63%n/an/a67.4%

What did safety testing find for Grok 4.7?

Safety level: xAI Frontier Artificial Intelligence Framework (FAIF, 30 June 2026): below the FAIF safety thresholds on dual-use knowledge

  • Grok 4.7 scores below the FAIF safety thresholds on dual-use biological knowledge, with no dual-use biological capability increase versus Grok 4.6.
  • Cyber: small capability gains over Grok 4.6, concentrated in defence and vulnerability mitigation; CyberGym 80.3% at high versus 79.7%, and third-party evaluators corroborated results on an unrestricted configuration.
  • HackerBench v0.3 with safeguards: 3.3% harmful or dual-use compliance per the launch post, with low benign refusal.
  • Jailbreak compliance at high effort: 0.01% standard, 2.0% StrongReject and 0.65% long-horizon, against 0.04%, 3.9% and 1.0% for Grok 4.6.
  • Self-harm compliance rises to 1.05% from 0.84% for Grok 4.6, and general refusal compliance is 1.10% against 0.93%.
  • MASK-Rectified dishonesty is 0.00% (Grok 4.6: 1.90%); child safety compliance is 0.0%.

Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our Grok 4.7 deep dive.

SpaceXAI Model Timeline

Grok 4.7Current

500k tokens context

Specifications

pricing$2/$6 per 1M tokens (input/output)
context Window500k tokens