Model Card: Grok 4.7
xAI's model card for Grok 4.7, dated September 21, 2026 on its cover, with a revision date of the same day.
- Issued by
- xAI
- Authors credited
- No authorship claim recorded yet. The source record lists xAI.
- Dates
- Published 2026-09-21 issue evidence
- Revised 2026-09-21
The cover prints the card's date, without a label, and 'Revision: 2026-09-21'; both are the same day.
- Exact source
- Model Card: Grok 4.7 xAI · published 2026-09-21 · Retrieved for the candidate pack on 2026-11-02 (SHA-256 c40541597ac3c461d71a914c922d43b200b468e41434b699fdd11c9a8761c56f) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. The archive capture was found by an index search of the Internet Archive on 2026-11-03; it was not opened, and its bytes are not authenticated.Archived copy, captured 2026-09-22: Model Card: Grok 4.7. Captured 1 day after the recorded version date. An archive copy shows only what the archive retrieved on 2026-09-22. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-11-02.
Appears in
No collection holds a record about this document yet.
Versions
xai-grok-4-7-model-card: 1 recorded version, oldest first, published by xAI. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2026-09-21 · revisedAs dated September 21, 2026 on its cover (Revision: 2026-09-21) (this version)
This version
Provisions in this version · 11 quoted · 5 not found
A limited selection of quoted provisions: what this edition says about thresholds, required actions, who decides and exceptions, and other statements of the text. It is not a full summary and says nothing about implementation. A “not found” record states which part of the edition was inspected. It is not a claim that the text was deleted.
- Model-card questionCard date“Model Card: Grok 4.7 September 21, 2026 Revision: 2026-09-21”Cover, PDF p. 1Inspect claim & evidence ↗
- Model-card questionRelease date“It is available for use through the following channels”§1.1 Overview, PDF p. 5 (printed p. 4)Inspect claim & evidence ↗
- Model-card questionFramework cited“treated as safety-threshold evaluations under the xAI Frontier Artificial Intelligence Framework (FAIF)”§7 Biological and chemical capabilities and safeguards, PDF p. 20 (printed p. 19)Inspect claim & evidence ↗
- Model-card questionLink to framework“xAI Frontier Artificial Intelligence Framework (FAIF). xAI, June 30, 2026.”References, item 16, PDF p. 29 (printed p. 28)Inspect claim & evidence ↗
- Model-card questionFramework determination“Grok 4.7 scores below the FAIF safety thresholds on dual-use knowledge”§7 Biological and chemical capabilities and safeguards, PDF p. 20 (printed p. 19)Inspect claim & evidence ↗
- Model-card questionSafeguards tied to determination“dedicated input and topical filters target biological and chemical weapons-related abuse”§9.3 CBRN / weapons refusals, PDF p. 25 (printed p. 24)Inspect claim & evidence ↗
- Model-card questionChemical and biological“Grok 4.7 scores below the FAIF safety thresholds on dual-use knowledge”§7 Biological and chemical capabilities and safeguards, PDF p. 20 (printed p. 19)Inspect claim & evidence ↗
- Model-card questionCyber“Grok 4.7 shows small cybersecurity-relevant capability gains over Grok 4.6”§6 Cyber capabilities and safeguards, PDF p. 17 (printed p. 16)Inspect claim & evidence ↗
- Model-card questionAlignment and deception“we test whether Grok 4.7 faithfully reports its beliefs when pressured to lie, as a proxy for the model's tendency to assert misleading information”§11.1 MASK-Rectified, PDF p. 26 (printed p. 25)Inspect claim & evidence ↗
- Model-card questionExternal testers“Results reported are taken from evaluations conducted by Datacurve.”§2.2 DeepSWE v1.1, note, PDF p. 8 (printed p. 7)Inspect claim & evidence ↗
- Model-card questionStated limits“the restricted task sets characterize the tested checkpoint and harness rather than establishing general biological safety or reliability”§7.1 BioSecBench, PDF p. 20 (printed p. 19)Inspect claim & evidence ↗
- Not found in the inspected textAutonomy and AI R&DInspected: Model Card: Grok 4.7: Whole card.Inspect claim & evidence ↗
- Not found in the inspected textPersuasionInspected: Model Card: Grok 4.7: Whole card.Inspect claim & evidence ↗
- Not found in the inspected textRed-teamingInspected: Model Card: Grok 4.7: Whole card.Inspect claim & evidence ↗
- Not found in the inspected textGovernment instituteInspected: Model Card: Grok 4.7: Whole card, including references and acknowledgements.Inspect claim & evidence ↗
- Not found in the inspected textRelease decisionInspected: Model Card: Grok 4.7: Whole card.Inspect claim & evidence ↗
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cites · 1
Explicit references in this document. Citation is neither agreement nor influence.
- xAI Frontier Artificial Intelligence Framework — June 2026 editionThe Grok 4.7 model card cites xAI's Frontier Artificial Intelligence Framework in a reference dated June 30, 2026, the June 2026 edition.2026-09-21 · publication · Stated in source · Supported Inspect claim & evidence ↗FAIF · June 2026 edition: document page →
Not recorded for this document: cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.