AIThe New Stackabout 2 hours ago
Fable 5.1 vs. Fable 5: Real-World Budget Benchmark
6 min read
Anthropic launched Claude Fable 5.1, highlighting a Terminal-Bench-Science score of 52.6% versus Fable 5's 24.7%. The benchmark grants models eight hours per task, and Anthropic has not disclosed the harness or budget used to produce its published score.
Level
Hype check
Tap to vote and see what everyone thinks.
