CookingBench

Results / v2.1 / Anthropic

Archived v2.1Unresolved leading group

Claude Fable 5

This profile reports Claude Fable 5’s original v2.1 result. It does not claim a timeless culinary rank. The run’s scoring limitations and later exploratory analyses are separate records.

Original overall

94.1

95% item-bootstrap interval

90.3–97.3

Frontier subset

87.1

Original score profile

Uncertainty and pairwise evidence

Claude Fable 5 belonged to a five-model group from which the run’s paired item-bootstrap rule did not identify one unique leader.

Scoring limitations

Saturated numeric items, high-influence keyword items and semantic constraint-check failures affected the instrument. The profile is retained as historical evidence, not validated culinary ability.

Run 2026-07-v2.1 · anthropic/claude-fable-5 · original artifact unchanged