Claude Fable 5 Isn't Nerfed. The Router Is Just Paranoid

BridgeBench's debugging score for Claude Fable 5 dropped from 86.2 to 25.9 after reinstatement, but the collapse was due to Anthropic's safety classifier routing most tasks to Opus 4.8, not a model degradation. Arena.AI blind human-preference tests found performance flat or improved, confirming the model itself wasn't nerfed.