# Claude Sonnet 4.6 vs GPT-5.4

As of Oct 15, 2026, Claude Sonnet 4.6 leads GPT-5.4 in 3 of 7 shared categories: Reasoning, Coding › Web dev, and Long context.

Claude Sonnet 4.6: $6 per 1M blended tokens.

GPT-5.4: $5.625 per 1M blended tokens.

Claude Sonnet 4.6: closed weights.

GPT-5.4: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-5.4 leads Claude Sonnet 4.6 in General LLM at #30 against #38.
- Which to pick, Reasoning: As of Oct 15, 2026, Claude Sonnet 4.6 leads GPT-5.4 in Reasoning at #20 against #32.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.4 leads Claude Sonnet 4.6 in Science at #16 against #50.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, Claude Sonnet 4.6 leads GPT-5.4 in Coding › Web dev at #43 against #60.
- Which to pick, Long context: As of Oct 15, 2026, Claude Sonnet 4.6 leads GPT-5.4 in Long context at #21 against #40.
- Which to pick, Factuality: As of Oct 15, 2026, GPT-5.4 leads Claude Sonnet 4.6 in Factuality at #6 against #38.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, GPT-5.4 leads Claude Sonnet 4.6 in Abstraction (ARC) at #10 against #23.

As of Oct 15, 2026, Claude Sonnet 4.6 is a former state-of-the-art holder in Long context (since Mar 19, 2026; sources LMArena Text (style-controlled, longer query); methodology v1.0).

As of Oct 15, 2026, GPT-5.4 is a former state-of-the-art holder in General LLM (since Apr 10, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).