Claude Opus 5.5

Reported Context (14)

In public files, the researchers found saved commands with the secret still inside, and they reproduced the behavior with the latest models, Opus 5.5 and Fable 5.1. Apiiro Finds Secrets in 1,122 Public Claude Code Settings Files
With American models configured on 3 different instances, we observed guardrails being hit only when using Anthropic’s Opus 5.5. ARTEX AI Agents Ran Largely Autonomous Cybercrime Campaigns, Check Point Finds
the attacker’s likely next move. Mythos 5.1 achieved the top first-guess accuracy at 39%, followed by Opus 5.5 (34%), Haiku 4.5 (15%), and Sonnet 4.6 (12%). ReliaQuest Describes Defensive Testing of Anthropic’s Claude Mythos
the attacker’s likely next move. Mythos 5.1 achieved the top first-guess accuracy at 39%, followed by Opus 5.5 (34%), Haiku 4.5 (15%), and Sonnet 4.6 (12%). ReliaQuest Reports Using Claude Mythos for Defensive Security Testing
and 71.0% on Collinear’s CWE-bench patching benchmark, topping OpenAI’s GPT-6 Astra and Anthropic’s Claude Opus 5.5 and Claude Fable 5.1 in the company’s comparison. Google Says Gemini 4 Carbon Leads Rivals on Vulnerability Benchmarks

CVE (6)

Malware (1)

People (12)

Threat Actors (5)

MITRE ATT&CK (13)

Vendors (43)

Products (66)

Tools (14)

Industries (22)

Countries (12)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.