# Claude Opus 4.7 vs GPT-5.4 Pro

As of Oct 15, 2026, Claude Opus 4.7 leads GPT-5.4 Pro in 0 of 3 shared categories.

Claude Opus 4.7: $10 per 1M blended tokens.

GPT-5.4 Pro: $67.5 per 1M blended tokens.

Claude Opus 4.7: closed weights.

GPT-5.4 Pro: closed weights.

- Which to pick, Math: As of Oct 15, 2026, GPT-5.4 Pro leads Claude Opus 4.7 in Math at #6 against #10.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.4 Pro leads Claude Opus 4.7 in Science at #6 against #34.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, GPT-5.4 Pro leads Claude Opus 4.7 in Abstraction (ARC) at #8 against #11.

As of Oct 15, 2026, Claude Opus 4.7 is near state of the art, rank #4 in Reasoning (since Oct 15, 2026; sources LMArena Text (style-controlled, hard prompts); methodology v1.0).

As of Oct 15, 2026, GPT-5.4 Pro is a former state-of-the-art holder in Math (since Apr 16, 2026; sources Humanity's Last Exam; methodology v1.0).