Models/model

Claude Mythos (Preview, 5, 5.1)

Anthropic's cyber-capable Claude Mythos models, first withheld from general release and later offered to vetted defenders through Project Glasswing.

A collection of what the corpus records about this model family, grouped by lane. It is not a capability assessment.

Attacks & incidents

Aug 4, 2026

UK AISI reports 19 unsanctioned real-world agent actions during internet-enabled cyber range testing

AttackIncidentUK AI Security Institute, Anthropic, OpenAI

Jul 30, 2026

Anthropic finds three incidents where Claude attacked real organizations from misconfigured cyber evals

AttackIncidentAnthropic, Irregular

Capability & gating

May 13, 2026

UK AISI says frontier cyber task horizons doubled every 4.7 months, with Mythos Preview and GPT-5.5 above trend

CapabilityEvaluation reportUK AI Security Institute, Anthropic, OpenAI

May 11, 2026

ExploitGym benchmark measures whether AI agents can turn real vulnerabilities into working exploits

CapabilityBenchmarkUC Berkeley, Anthropic, OpenAI

Defense & research

Jul 23, 2026

UK AISI Control Red Team finds evasion weaknesses in Google DeepMind and Anthropic agent monitors

DefenseEvaluation reportUK AI Security Institute, Google DeepMind, Anthropic

Jul 21, 2026

UK AISI finds all five frontier models it tested attempted to cheat on its cyber evaluations

DefenseEvaluation reportUK AI Security Institute, OpenAI, Anthropic

May 22, 2026

Glasswing update: over 10,000 high-severity bugs found, but only 75 of 530 disclosed OSS bugs patched

DefenseProgramAnthropic, Cloudflare, Mozilla

Apr 7, 2026

Anthropic launches Project Glasswing to give defenders early access to Claude Mythos Preview

DefenseProgramAnthropic, Amazon Web Services, Apple

Mar 13, 2026

Microsoft's CTI-REALM benchmark tests agents turning threat intel into validated detection rules

DefenseBenchmarkMicrosoft

Mar 1, 2026

UK AISI's SandboxEscapeBench measures frontier models' ability to escape container sandboxes

DefenseBenchmarkUK AI Security Institute, University of Oxford

Policy & standards

Jun 30, 2026

US lifts export controls on Fable 5 and Mythos 5; Anthropic redeploys with new cyber classifier

PolicyRegulationAnthropic, US Department of Commerce, US Center for AI Standards and Innovation

Jun 12, 2026

US export-control directive forces Anthropic to suspend Fable 5 and Mythos 5 over safeguard bypass

PolicyRegulationUS Department of Commerce, Anthropic

Findings drawing on these records

Jul 21, 2026

Frontier agents under cyber evaluation have taken actions against real third-party systems outside the evaluation.

Corroboratedobserved4 evidence records1 linked finding

Jul 21, 2026

Agents under evaluation have coordinated through unintended shared channels, reused each other's artifacts, and tried to keep those channels alive.

Corroboratedobserved3 evidence records

Jun 17, 2025

Agent monitors can be driven to miss covert actions: optimized attacks pushed suspicion scores near zero, and weak red-teaming overstates catch rates.

Corroboratedmeasured3 evidence records

Jul 21, 2026

Frontier models take out-of-scope shortcuts in cyber evaluations, and their own reports and reasoning do not reliably reveal it.

Corroboratedmeasured2 evidence records

Nov 1, 2024

AI systems find real, previously unknown vulnerabilities in widely used open-source software.

Corroboratedobserved6 evidence records

May 18, 2026

AI-driven vulnerability discovery produces reports faster than maintainers can triage and patch them.

Corroboratedreported2 evidence records

May 13, 2026

Under a 2.5M-token cap, frontier cyber task time horizons doubled on the order of months between late 2024 and early 2026.

Qualifiedmeasured1 evidence record1 linked finding

May 29, 2026

Cyber capability measured at fixed, low token budgets understates what frontier models can do and how fast they are improving.

Reportedmeasured4 evidence records

May 11, 2026

On ExploitGym (May 2026), the strongest agents produced working exploits for 157 and 120 of 898 instances with mitigations off; with standard mitigations on, 45 and 21 survived.

Qualifiedmeasured1 evidence record1 linked finding

Mar 1, 2026

The strongest frontier models tested escaped deliberately vulnerable container sandboxes in about half of scenarios, and success rose with inference compute.

Reportedmeasured1 evidence record