Values by metric family

Each value as the document printed it. Select a value for its source, its checks and its history. Values from other documents are listed after the model’s own, each marked as the first report of that measure or as a restatement.

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

M1 · Evaluation awareness 1 value

M1 Evaluation awareness: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Evaluation awareness in audit transcriptsShare of transcripts with eval awarenessCondition: white-box/unverbalized detectionClaude Mythos Preview System Card7 Apr 2026

M2 · Reward hacking 3 values

M2 Reward hacking: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
GUI computer-use impossible tasksReward hack rateCondition: anti-hack promptClaude Mythos Preview System Card7 Apr 2026
Impossible tasksReward hack rateCondition: anti-hack promptClaude Mythos Preview System Card7 Apr 2026
Impossible tasksReward hack rateCondition: no anti-hack promptClaude Mythos Preview System Card7 Apr 2026

M3 · Sabotage and sandbagging 5 values

M3 Sabotage and sandbagging: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Minimal-LinuxBenchStealth success rateCondition: CoT visible to monitorClaude Mythos Preview System Card7 Apr 2026
Sandbagging transcript reviewPossible sandbagging casesCondition: 20 flagged transcripts human-reviewedClaude Mythos Preview System Card7 Apr 2026
SHADE-ArenaStealth success rateCondition: extended thinkingRestated later: compare with the later valueClaude Mythos Preview System Card7 Apr 2026Restated later: compare with the later value
SHADE-ArenaStealth success rateCondition: hidden scratchpadClaude Mythos Preview System Card7 Apr 2026
From other documents
SHADE-ArenaStealth success rateCondition: extended thinkingClaude Opus 4.7 System Card16 Apr 2026Restated: compare with the earlier valueClaude Opus 4.7 System Card16 Apr 2026Restated: compare with the earlier value

M4 · Misalignment audits 3 values

M4 Misalignment audits: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Automated behavioral auditOverall misaligned behavior scoreClaude Mythos Preview System Card7 Apr 2026
Destructive actions (synthetic backend)Destructive action rateClaude Mythos Preview System Card7 Apr 2026
Internal deployment monitoringCovering tracks after disallowed actionsCondition: earlier snapshotsClaude Mythos Preview System Card7 Apr 2026

M5 · Honesty and hallucination 4 values

M5 Honesty and hallucination: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
100Q-HardCorrect answer rateClaude Mythos Preview System Card7 Apr 2026
False-premise honestyHonest pushback rateClaude Mythos Preview System Card7 Apr 2026
MASKHonesty rate under pressureClaude Mythos Preview System Card7 Apr 2026
From other documents
Agentic code summary honestyFailure to report important eventsClaude Opus 4.8 System Card28 May 2026First reportedClaude Opus 4.8 System Card28 May 2026First reported

M6 · Sycophancy 1 value

M6 Sycophancy: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Automated behavioral auditSycophancy scoreClaude Mythos Preview System Card7 Apr 2026

M7 · Harmful compliance and over-refusal 5 values

M7 Harmful compliance and over-refusal: values about Claude Mythos Preview
Evaluation and metricValueDocument
From other documents
Single-turn benign requestsOver-refusal rateCondition: no system prompt; APIClaude Opus 4.8 System Card28 May 2026First reportedClaude Opus 4.8 System Card28 May 2026First reported
Single-turn violative requestsHarmless response rateCondition: no system prompt; APIClaude Opus 4.8 System Card28 May 2026First reportedRestated later: compare with the later valueClaude Opus 4.8 System Card28 May 2026First reportedRestated later: compare with the later value
Malicious Claude Code useRefusal rate, malicious requestsClaude Sonnet 5 System Card30 Jun 2026First reportedClaude Sonnet 5 System Card30 Jun 2026First reported
Malicious computer useRefusal rateClaude Sonnet 5 System Card30 Jun 2026First reportedClaude Sonnet 5 System Card30 Jun 2026First reported
Single-turn violative requestsHarmless response rateCondition: no system prompt; APIClaude Sonnet 5 System Card30 Jun 2026Restated: compare with the earlier valueClaude Sonnet 5 System Card30 Jun 2026Restated: compare with the earlier value

M10 · Dangerous capabilities and risk determinations 21 values

M10 Dangerous capabilities and risk determinations: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
AI R&D kernel taskBest speedupClaude Mythos Preview System Card7 Apr 2026
AI R&D LLM training taskAverage speedupRestated later: compare with the later valueClaude Mythos Preview System Card7 Apr 2026Restated later: compare with the later value
AI R&D novel compiler taskPass rateClaude Mythos Preview System Card7 Apr 2026
Autonomy threat model 2 (automated R&D)RSP determinationClaude Mythos Preview System Card7 Apr 2026
CB-1 threat modelRSP determinationClaude Mythos Preview System Card7 Apr 2026
CB-2 threat modelRSP determinationClaude Mythos Preview System Card7 Apr 2026
CybenchSuccess rate, pass@1Condition: 35 challengesClaude Mythos Preview System Card7 Apr 2026
CyberGymTargeted vuln reproduction rateRestated later: compare with the later valueClaude Mythos Preview System Card7 Apr 2026Restated later: compare with the later value
Internal AI R&D suite 2Suite scoreClaude Mythos Preview System Card7 Apr 2026
Internal AI R&D surveyRespondents saying drop-in entry-level researcher nowCondition: of 18 respondentsClaude Mythos Preview System Card7 Apr 2026
Multimodal virology (VCT)ScoreClaude Mythos Preview System Card7 Apr 2026
Release decisionDeployment scopeClaude Mythos Preview System Card7 Apr 2026
Virology protocol uplift trialMean critical failuresCondition: model-assistedClaude Mythos Preview System Card7 Apr 2026
From other documents
AI R&D LLM training taskAverage speedupClaude Opus 4.7 System Card16 Apr 2026Restated: compare with the earlier valueClaude Opus 4.7 System Card16 Apr 2026Restated: compare with the earlier value
Cyber rangeFull range solvesCondition: 10 attemptsRun by UK AI Security InstituteClaude Opus 4.7 System Card16 Apr 2026First reportedClaude Opus 4.7 System Card16 Apr 2026First reported
Anthropic ECI (AECI)Capability indexClaude Opus 4.8 System Card28 May 2026First reportedClaude Opus 4.8 System Card28 May 2026First reported
CyberGymTargeted vuln reproduction rateClaude Opus 4.8 System Card28 May 2026Restated: compare with the earlier valueClaude Opus 4.8 System Card28 May 2026Restated: compare with the earlier value
Firefox 147 exploitationFull exploit rateCondition: without safeguardsClaude Opus 4.8 System Card28 May 2026First reportedClaude Opus 4.8 System Card28 May 2026First reported
AI R&D LLM training taskAverage speedupCondition: re-runClaude Fable 5 & Claude Mythos 5 System Card9 Jun 2026Restated: compare with the earlier valueClaude Fable 5 & Claude Mythos 5 System Card9 Jun 2026Restated: compare with the earlier value
Anthropic ECI (AECI)Capability indexClaude Fable 5 & Claude Mythos 5 System Card9 Jun 2026First reportedClaude Fable 5 & Claude Mythos 5 System Card9 Jun 2026First reported
Anthropic ECI (AECI)Capability indexClaude Opus 5.5 System Card22 Sep 2026First reportedClaude Opus 5.5 System Card22 Sep 2026First reported

M11 · Self-preservation 1 value

M11 Self-preservation: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Sandbox escape incidentReal-world incident reportedCondition: internal useClaude Mythos Preview System Card7 Apr 2026

M12 · Chain-of-thought monitorability 1 value

M12 Chain-of-thought monitorability: values about Claude Mythos Preview
Evaluation and metricValueDocument
From its own documentClaude Mythos Preview System Card · 7 Apr 2026
Encoded reasoning (scratchpad paraphrase)Pass@1 with paraphrased scratchpadClaude Mythos Preview System Card7 Apr 2026

Restated in later documents

A later document reported values about Claude Mythos Preview again. Each pair is shown side by side: both values are kept with their own documents, and the later one does not replace the earlier.

Values about Claude Mythos Preview restated in later documents
Earlier valueLater value
M3 · Sabotage and sandbagging
SHADE-ArenaStealth success rateCondition: extended thinking
Claude Mythos Preview System Card7 Apr 2026 · its own documentClaude Opus 4.7 System Card16 Apr 2026No reason stated
M7 · Harmful compliance and over-refusal
Single-turn violative requestsHarmless response rateCondition: no system prompt; API
Claude Opus 4.8 System Card28 May 2026 · first reportedClaude Sonnet 5 System Card30 Jun 2026No reason stated
M10 · Dangerous capabilities and risk determinations
AI R&D LLM training taskAverage speedup
Claude Mythos Preview System Card7 Apr 2026 · its own documentClaude Opus 4.7 System Card16 Apr 2026No reason stated
AI R&D LLM training taskAverage speedupLater condition: re-run
Claude Mythos Preview System Card7 Apr 2026 · its own documentClaude Fable 5 & Claude Mythos 5 System Card9 Jun 2026Reason stated: re-run
CyberGymTargeted vuln reproduction rate
Claude Mythos Preview System Card7 Apr 2026 · its own documentClaude Opus 4.8 System Card28 May 2026No reason stated

Risk determinations

The developer's formal decisions about Claude Mythos Preview under its framework, as printed. Levels from different frameworks do not map onto one another.

Risk determinations about Claude Mythos Preview
DomainLevel as printedFramework and document
Bio/chemapplicable code, not the printed wording Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026
Bio/chemnot applicable Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026
AI R&D / autonomynot applicable Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026Responsible Scaling Policy, version 3.0 Claude Mythos Preview System Card · 7 Apr 2026

“Code, not the printed wording”: the version 0 file stored a code for this level rather than the words the document printed. The wording will be read again from the source.