# Claude Opus 4.6 vs GPT-5

As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Coding › Web dev, Long context, and Factuality.

Claude Opus 4.6: $10 per 1M blended tokens.

GPT-5: $3.4375000000000004 per 1M blended tokens.

Claude Opus 4.6: closed weights.

GPT-5: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in General LLM at #4 against #76.
- Which to pick, Reasoning: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Reasoning at #2 against #78.
- Which to pick, Math: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Math at #11 against #15.
- Which to pick, Science: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Science at #32 against #54.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Coding › Web dev at #35 against #66.
- Which to pick, Long context: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Long context at #2 against #107.
- Which to pick, Factuality: As of Oct 14, 2026, Claude Opus 4.6 leads GPT-5 in Factuality at #3 against #93.

As of Oct 14, 2026, Claude Opus 4.6 is near state of the art, rank #2 in Reasoning (since Oct 14, 2026; sources LMArena Text (style-controlled, hard prompts); methodology v1.0).

As of Oct 14, 2026, GPT-5 is a former state-of-the-art holder in General LLM (since Aug 27, 2025; sources LMArena Text (style-controlled, overall); methodology v1.0).