{"data":{"id":"6200001a-3646-41c2-a106-ffd86d8c5ca2","title":"AI Safety Newsletter #66: Evaluating Frontier Models, New Gemini and Claude, Preemption is Back","summary":"The Center for AI Safety launched an AI Dashboard that evaluates frontier AI models (the most advanced AI systems currently available) on capability and safety benchmarks, ranking them across text, vision, and risk categories. The Risk Index specifically measures how likely models are to exhibit dangerous behaviors like dual-use biology assistance (helping with harmful biological research), jailbreaking vulnerability (susceptibility to tricks that bypass safety features), overconfidence, deception, and harmful actions, with Claude Opus 4.5 currently scoring safest at 33.6 on a 0-100 scale (lower is safer). The dashboard also tracks industry progress toward broader automation milestones like AGI (artificial general intelligence, systems that can perform any intellectual task) and self-driving vehicles.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://newsletter.safe.ai/p/ai-safety-newsletter-66-aisn-66-evaluating","publishedAt":"2025-12-02T01:35:41.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":["Anthropic","Google"],"affectedVendorsRaw":["Anthropic","Claude Opus 4.5","Google","Gemini"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}