This is a
results-tracking model card for the API model
Claude Fable 5. It
holds no weights. Its purpose is to host evaluation results for
RedlineBench on the
Hugging Face Hub, since Claude Fable 5 has no public model repository.
Results live in
.eval_results/. Scores are attributed to the
published report (community/source — not HF-
verified, which is inspect-ai-only).
