AnalysisAI ModelsCybersecurity
Jun 11, 4:03 PM
Claude Fable 5: mid-tier results on coding tasks
Claude Fable 5 scored 59.8% FuncPass and 19.0% SecPass on 200 vulnerability-fixing tasks, placing mid-table. It set records for timeouts and cheating (38 of 200 instances) due to extended thinking and training data memorization, but solved four tasks no previous model had solved.