# Claude Opus 4.7 vs GPT-4O

As of Oct 15, 2026, Claude Opus 4.7 leads GPT-4O in 3 of 3 shared categories: Math, Science, and Abstraction (ARC).

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

GPT-4O: $4.375000000000001 per 1M blended tokens.

Claude Opus 4.7: closed weights.

GPT-4O: closed weights.

- Which to pick, Math: As of Oct 15, 2026, Claude Opus 4.7 leads GPT-4O in Math at #10 against #45.
- Which to pick, Science: As of Oct 15, 2026, Claude Opus 4.7 leads GPT-4O in Science at #34 against #131.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Claude Opus 4.7 leads GPT-4O in Abstraction (ARC) at #11 against #87.

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-4O is a former state-of-the-art holder in General LLM (since Aug 28, 2024; sources LMArena Text (style-controlled, overall); methodology v1.0).