Claude Mythos Preview
READER SUMMARYA restricted general-purpose frontier preview with exceptional autonomous vulnerability discovery and exploitation capability, deployed to vetted Project Glasswing cyber defenders.
Why this model scores 77.7
Claude Mythos Preview surpassed nearly all human experts on key vulnerability tasks and completed sustained simulated network attacks, while live restricted deployment found thousands of severe flaws. Strict partner access keeps deployment low, but the capability's offensive dual use and acknowledged lack of robust general-release safeguards create high misuse and residual control difficulty.
News tied to Claude Mythos Preview
The model score of 77.7 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.
Anthropic expands Mythos Preview access to 150 critical organizations
Anthropic expanded Project Glasswing access to Claude Mythos Preview by about 150 organizations across more than 15 countries, prioritizing power, water, healthcare, communications, hardware, and critical software providers.
- Full item contribution
- +0.11
- Claude Mythos Preview equal share
- +0.11
Claude Mythos Preview finds over 10,000 severe software vulnerabilities
Anthropic reported that Project Glasswing's restricted Claude Mythos Preview deployment found more than 10,000 high- or critical-severity vulnerabilities across systemically important software.
- Full item contribution
- +0.18
- Claude Mythos Preview equal share
- +0.18
UK AISI finds autonomous cyber task horizons doubling every few months
UK AISI found that frontier models' 80-percent-reliability cyber task horizon had doubled every 4.7 months since late 2024, with GPT-5.5 and Claude Mythos Preview exceeding that trend in sustained simulated attacks.
- Full item contribution
- +0.16
- Claude Mythos Preview equal share
- +0.08
Anthropic deploys safeguards against autonomous election influence operations
Anthropic reported always-on classifiers, monitoring, system prompts, and election controls that caused safeguarded models to refuse nearly all autonomous influence-operation tasks despite strong raw capability.
- Full item contribution
- -0.24
- Claude Mythos Preview equal share
- -0.08
UK AISI finds Claude Mythos Preview can autonomously take over a simulated corporate network
UK AISI found Claude Mythos Preview completed a 32-step corporate-network takeover in three of ten attempts; Anthropic later verified practical downstream impact through large-scale real-world vulnerability discovery.
- Full item contribution
- +0.12
- Claude Mythos Preview equal share
- +0.12
Anthropic gates Claude Mythos Preview after step-change cyber results
Anthropic reported that Claude Mythos Preview found and exploited serious real-world vulnerabilities, while restricting the model to a gated defensive research program rather than general release.
- Full item contribution
- +0.13
- Claude Mythos Preview equal share
- +0.13
Model score history
- R2Doom Score 77.7
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 79.6
Initial exact-tier profile from the dated model assessment and separately verified Project Glasswing deployment results.
11 Aug 2026