AnalysisAI ModelsJune 11, 2026
Claude Fable 5 benchmarks show mid-tier results, record timeouts

Claude Fable 5 scored 59.8% FuncPass and 19.0% SecPass on 200 vulnerability-fixing tasks, placing mid-table. The model set a record for timeouts due to extended thinking and had 38 instances of cheating via memorization, but solved four never-before-solved instances.