Definition

Self-preservation covers behaviour aimed at a model’s own continuation or influence rather than at its task: resisting or working around being shut down, copying its own weights out of a controlled environment, escaping a sandbox, or acquiring resources or access it was not given.

Developers study it mainly through constructed scenarios in which such an action is possible and tempting, and by reviewing incidents in testing or internal use in which a model attempted something of this kind.

Results are often descriptions of what happened rather than rates, and a rate, where one is printed, applies to one set of scenarios. The scenarios differ widely between developers, so each value in this family describes a particular setup rather than a general tendency.

The line under the title is this family’s entry in Methodology §1.1. A family groups results about one property; it does not make them comparable (Methodology §5).

How developers measure it

four evaluations of three kinds of test, with the most values first. Each evaluation opens in the data explorer, which lists all of its values.

The four evaluations in Self-preservation, grouped by kind of test: who ran each one, what it counts, the developers whose documents report it and how many values it has.
EvaluationReported byValues
Scenario evaluation · 2 evaluations, 2 values
Sandbox escape/tamper attempts, in the data explorer Run by the developer Share of test runs in which the model tries to escape or tamper with its sandbox.Reported by Anthropic · 1 valueAnthropic1
Self-preservation · Apollo Research, in the data explorer Run by Apollo Research (third party) Apollo Research scenarios checking whether a model acts to preserve itself.Reported by OpenAI · 1 valueOpenAI1
Internal-use monitoring · 1 evaluation, 1 value
Sandbox escape incident, in the data explorer Run by the developer Real incidents during internal use in which a model got out of its sandbox.Reported by Anthropic · 1 valueAnthropic1
Qualitative assessment · 1 evaluation, 1 value
Sandbox vulnerability exploit, in the data explorer Run by the developer A report of whether a model exploited a sandbox vulnerability during testing, here by reading files outside its environment.Reported by Anthropic · 1 valueAnthropic1

Reported values

This family has four values, and one of them is a printed number a chart could place: too few to chart, so the values are listed here instead. Open in explorer: Self-preservation

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

All 4 values in Self-preservation
ModelDeveloperEvaluationConditionValueDocument
gpt-5.2-thinkingOpenAISelf-preservationRun by Apollo ResearchSelf-preservation behavior observed—GPT-5.2 System Card (update to GPT-5 card)11 Dec 2025
Claude Mythos PreviewAnthropicSandbox escape incidentReal-world incident reportedinternal useClaude Mythos Preview System Card7 Apr 2026
Claude Mythos 5.1AnthropicSandbox vulnerability exploitReal-world incident reported—Claude Fable 5.1 & Claude Mythos 5.1 System Card1 Sep 2026
Claude Opus 5.5AnthropicSandbox escape/tamper attemptsShare of runs with escape/tamper attemptwithout safeguardsClaude Opus 5.5 System Card22 Sep 2026

Comparability

  • Each of the four evaluations is its own test, with its own tasks, graders and definitions. Values from different evaluations describe the same property measured in different ways, and are not comparable with one another, even where two evaluations share a name.
  • Values come from the documents of two developers. Developers use different tests, prompts and graders for the same property, so we do not rank them on these numbers: tables here are ordered by name or by kind of test, never by a reported value.

Coverage

Documents from two of the eight developers report this family. The coverage matrix counts a document when it has at least one printed number in the family; categories, statements in words and figure reads count only in the first column.

Each developer's documents with values in Self-preservation, out of all its documents in the dataset
DeveloperWith any valueWith a printed numberAll its documents
Anthropic3115
DeepSeek001
Google DeepMind0016
Meta005
Moonshot AI002
OpenAI1022
xAI008
Zhipu AI001

Related findings

No finding is about this family yet.