# Claude Opus 5.5 vs GPT-4.1 Nano

As of Oct 15, 2026, Claude Opus 5.5 leads GPT-4.1 Nano in 2 of 2 shared categories: Science and Abstraction (ARC).

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

GPT-4.1 Nano: $0.175 per 1M blended tokens.

Claude Opus 5.5: closed weights.

GPT-4.1 Nano: closed weights.

- Which to pick, Science: As of Oct 15, 2026, Claude Opus 5.5 leads GPT-4.1 Nano in Science at #31 against #129.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Claude Opus 5.5 leads GPT-4.1 Nano in Abstraction (ARC) at #1 against #91.

As of Oct 15, 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 15, 2026, GPT-4.1 Nano is ranked #91 in Abstraction (ARC) (since Oct 15, 2026; sources ARC-AGI; methodology v1.0).