# Claude Fable 5.1 vs Claude Sonnet 4

As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in 5 of 5 shared categories: General LLM, Reasoning, Math, Long context, and Abstraction (ARC).

Claude Fable 5.1: $20 per 1M blended tokens.

Claude Sonnet 4: $6 per 1M blended tokens.

Claude Fable 5.1: closed weights.

Claude Sonnet 4: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in General LLM at #6 against #126.
- Which to pick, Reasoning: As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in Reasoning at #5 against #115.
- Which to pick, Math: As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in Math at #2 against #35.
- Which to pick, Long context: As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in Long context at #6 against #94.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, Claude Fable 5.1 leads Claude Sonnet 4 in Abstraction (ARC) at #3 against #67.

As of Oct 14, 2026, Claude Fable 5.1 is tied for state of the art in Factuality (since Oct 2, 2026; sources LMArena Text factuality; methodology v1.0).

As of Oct 14, 2026, Claude Sonnet 4 is ranked #35 in Math (since Oct 14, 2026; sources Humanity's Last Exam; methodology v1.0).