# Claude Opus 5.5 vs GPT-6 Luna

As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in 10 of 10 shared categories: General LLM, Reasoning, Science, Coding, Coding › Agentic, Coding › Web dev, Long context, Vision, Factuality, and Abstraction (ARC).

Claude Opus 5.5: $8.000000000000002 per 1M blended tokens.

GPT-6 Luna: $0.19999999999999998 per 1M blended tokens.

Claude Opus 5.5: closed weights.

GPT-6 Luna: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in General LLM at #2 against #65.
- Which to pick, Reasoning: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Reasoning at #1 against #61.
- Which to pick, Science: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Science at #31 against #33.
- Which to pick, Coding: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Coding at #1 against #17.
- Which to pick, Coding › Agentic: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Coding › Agentic at #1 against #17.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Coding › Web dev at #1 against #29.
- Which to pick, Long context: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Long context at #1 against #61.
- Which to pick, Vision: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Vision at #4 against #17.
- Which to pick, Factuality: As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Factuality at #1 against #39.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, Claude Opus 5.5 leads GPT-6 Luna in Abstraction (ARC) at #1 against #22.

As of Oct 14, 2026, Claude Opus 5.5 is tied for state of the art in Reasoning (since Oct 2, 2026; sources LMArena Text (style-controlled, hard prompts); methodology v1.0).

As of Oct 14, 2026, GPT-6 Luna is state of the art on best per dollar in Coding (since Oct 14, 2026; sources Terminal-Bench 4.0; methodology v1.0).