BREAKING
Claude Fable 5 BridgeBench Scores Drop
From Launch to Redeploy
1Released June 9
2Export ban June 12
3Suspended
4Redeployed July 1
BridgeBench Debugging: 86.2 to 25.9
Before86.2
After25.9
Declines Across Categories
Debug25.9
Refactor38.4
Halluc.61.7
Safety vs Usability Debate
BeforeOriginal
Fallback under 5% of sessions
Top coding scores
AfterRedeployed
Fallback fires on ordinary tasks
Developers cite reduced usefulness
Safety and Usability Debate Goes On
AI NEWS BLITZ
Anthropic's redeployed Claude Fable 5 just posted sharply lower benchmark scores.