Versions

One version is on record: the copy we retrieved on 26 Sep 2026. We know of no other.

  1. 26 Sep 2026

    Date retrieved

    Copy retrieved 26 Sep 2026

    Date from
    the date we retrieved it; the copy states no version date
    Copy
    Copy retrieved on 26 Sep 2026
    Values
    14 values recorded from this version

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. None has been blind-verified yet.

KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.

M5 Honesty and hallucination

1 value

M5 Honesty and hallucination: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 ThinkingMASKDishonesty ratereasoningTable 3Unverified

M6 Sycophancy

2 values

M6 Sycophancy: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 Non-ThinkingSycophancySycophancy ratenon-reasoningTable 3Unverified
Grok 4.1 ThinkingSycophancySycophancy ratereasoningTable 3Unverified

M7 Harmful compliance and over-refusal

3 values

M7 Harmful compliance and over-refusal: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 Non-ThinkingRefusalsAnswer rate on should-refuse promptsnon-reasoning; production system promptTable 1Unverified
Grok 4.1 ThinkingAgentHarmAnswer rate on harmful agentic tasksreasoning; no attackTable 1Unverified
Grok 4.1 ThinkingRefusalsAnswer rate on should-refuse promptsreasoning; production system promptTable 1Unverified

M8 Jailbreak robustness

2 values

M8 Jailbreak robustness: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 ThinkingJailbreaksAnswer rate on should-refuse promptsreasoning; user jailbreakTable 1Unverified
Grok 4.1 (input filter)Restricted-bio input filterFalse negative ratewith prompt injection attackTable 2Unverified

M9 Prompt injection

1 value

M9 Prompt injection: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 ThinkingAgentDojoPrompt-injection attack success ratereasoning; production system promptTable 1Unverified

M10 Dangerous capabilities and risk determinations

5 values

M10 Dangerous capabilities and risk determinations: values in the Grok 4.1 Model Card
ModelEvaluationConditionValueLocationChecked
Grok 4.1 ThinkingBioLP-BenchAccuracyreasoning; without safeguardsTable 4Unverified
Grok 4.1 ThinkingCloningScenariosAccuracyreasoning; without safeguardsTable 4Unverified
Grok 4.1 ThinkingCybenchUnguided success ratereasoning; without safeguardsTable 4Unverified
Grok 4.1 ThinkingMakeMeSayPersuasion win ratereasoningTable 4Unverified
Grok 4.1 ThinkingVCTAccuracyreasoning; without safeguardsTable 4Unverified

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 14 values were read in the document itself.

All 14 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).