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
    4 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.

M7 Harmful compliance and over-refusal

1 value

M7 Harmful compliance and over-refusal: values in the Kimi K2 technical report
ModelEvaluationConditionValueLocationChecked
Kimi K2-InstructPromptfoo red-team (no attack)Harmful: pass rate (safe responses)Basic (no attack)Table 6Unverified

M8 Jailbreak robustness

2 values

M8 Jailbreak robustness: values in the Kimi K2 technical report
ModelEvaluationConditionValueLocationChecked
Kimi K2-InstructPromptfoo red-teamHarmful: pass rate (safe responses)Crescendo multi-turnTable 6Unverified
Kimi K2-InstructPromptfoo red-teamHarmful: pass rate (safe responses)Iterative JailbreakTable 6Unverified

M9 Prompt injection

1 value

M9 Prompt injection: values in the Kimi K2 technical report
ModelEvaluationConditionValueLocationChecked
Kimi K2-InstructPromptfoo red-team (prompt injection)Harmful: pass rate (safe responses)Prompt injectionTable 6Unverified

Extraction coverage

What we read of this document, and where each value was read.

Our note Red-team pass rates

All 4 values were read in the document itself.

All 4 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).