# GPT-5.4 vs O4 Mini

As of Oct 14, 2026, GPT-5.4 leads O4 Mini in 6 of 6 shared categories: General LLM, Reasoning, Math, Science, Factuality, and Abstraction (ARC).

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

O4 Mini: $1.9250000000000003 per 1M blended tokens.

GPT-5.4: closed weights.

O4 Mini: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, GPT-5.4 leads O4 Mini in General LLM at #28 against #125.
- Which to pick, Reasoning: As of Oct 14, 2026, GPT-5.4 leads O4 Mini in Reasoning at #29 against #129.
- Which to pick, Math: As of Oct 14, 2026, GPT-5.4 leads O4 Mini in Math at #9 against #23.
- Which to pick, Science: As of Oct 14, 2026, GPT-5.4 leads O4 Mini in Science at #16 against #70.
- Which to pick, Factuality: As of Oct 14, 2026, GPT-5.4 leads O4 Mini in Factuality at #6 against #122.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 leads O4 Mini in Abstraction (ARC) at #10 against #39.

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, O4 Mini is a former state-of-the-art holder in Math (since Jul 20, 2025; sources Humanity's Last Exam; methodology v1.0).