Grok 4.7 Model Card
A model card by xAI about Grok 4.7, published 21 Sep 2026. We recorded 11 values from it.
- Developer
- xAI
- Type
- Model card
- Model covered
- Grok 4.7
- Published
- 21 Sep 2026
- Archived copy
- No archived copy yet
- Changelog
- No changelog
Data as of 26 Sep 2026 · Dataset v0.1 · Methodology v0.1 · Changelog
Versions
One version is on record: the copy we retrieved on 26 Sep 2026. We know of no other.
26 Sep 2026
Date retrieved
Copy retrieved 26 Sep 2026
No version has a file hash or an archived snapshot yet. From dataset v0.2 each retrieved version carries both (Methodology §7).
Revisions
No revisions are recorded for this document. We know of only one version of it.
Values
Every value we recorded from this document, grouped by metric family and ordered by where the document prints it. Location is the section, table or page as the document numbers it. 1 of the 11 has been blind-verified: a second reader found the same value without seeing ours.
KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.
M5 Honesty and hallucination
1 value
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Grok 4.7 (high) | MASK-RectifiedDishonesty rate | high | 11.1 | Unverified |
M6 Sycophancy
1 value
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Grok 4.7 (high) | SycophancySycophancy rate | high | 11.2 | Verified |
M7 Harmful compliance and over-refusal
5 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Grok 4.6 (high) | HackerBenchCompliance on harmful/dual-use cyber tasks | high | 6.3 | Unverified | |
| Grok 4.7 (high) | HackerBenchCompliance on harmful/dual-use cyber tasks | high | 6.3 | Unverified | |
| Grok 4.7 (high) | BioUseBenchDual-use bio refusal rate | high | 7.4 | Unverified | |
| Grok 4.7 (high) | RefusalsCompliance on should-refuse prompts | high; full safeguards | 9.1 | Unverified | |
| Grok 4.7 (high) | Self-harm refusalsCompliance (non-refusal/redirect) | high | 10.1 | Unverified |
M8 Jailbreak robustness
1 value
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Grok 4.7 (high) | StrongREJECTCompliance under StrongREJECT attacks | high | 8.1 | Unverified |
M10 Dangerous capabilities and risk determinations
3 values
| Model | Evaluation | Condition | Value | Location | Checked |
|---|---|---|---|---|---|
| Grok 4.7 (high) | CyberGymMean vulnerabilities reproduced | high; unrestricted | 6.1 | Unverified | |
| Grok 4.7 | Dual-use bio determinationThreshold statement | None stated | 7 | Unverified | |
| Grok 4.7 (high) | VCTAccuracy | high | 7.2 | Unverified |
Extraction coverage
What we read of this document, and where each value was read.
Our note We have not written a coverage note for this document yet.
All 11 values were read in the document itself.
All 11 values were extracted for version 0 of the dataset through a web reader, which did not always reach the later sections of long PDFs (Methodology §3).