# GPT-5.4 vs O1

As of Oct 14, 2026, GPT-5.4 leads O1 in 6 of 6 shared categories: General LLM, Reasoning, Math, Science, Long context, and Abstraction (ARC).

GPT-5.4: $5.625 per 1M blended tokens.

O1: $26.25 per 1M blended tokens.

GPT-5.4: closed weights.

O1: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, GPT-5.4 leads O1 in General LLM at #28 against #112.
- Which to pick, Reasoning: As of Oct 14, 2026, GPT-5.4 leads O1 in Reasoning at #29 against #117.
- Which to pick, Math: As of Oct 14, 2026, GPT-5.4 leads O1 in Math at #9 against #34.
- Which to pick, Science: As of Oct 14, 2026, GPT-5.4 leads O1 in Science at #16 against #77.
- Which to pick, Long context: As of Oct 14, 2026, GPT-5.4 leads O1 in Long context at #34 against #108.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 leads O1 in Abstraction (ARC) at #10 against #57.

As of Oct 14, 2026, GPT-5.4 is a former state-of-the-art holder in General LLM (since Apr 10, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).

As of Oct 14, 2026, O1 is a former state-of-the-art holder in General LLM (since Jan 28, 2025; sources LMArena Text (style-controlled, overall); methodology v1.0).