# GPT-4.1 vs GPT-5.4

As of Oct 14, 2026, GPT-4.1 leads GPT-5.4 in 0 of 7 shared categories.

GPT-4.1: $3.5 per 1M blended tokens.

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

GPT-4.1: closed weights.

GPT-5.4: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in General LLM at #28 against #101.
- Which to pick, Reasoning: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Reasoning at #29 against #102.
- Which to pick, Math: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Math at #9 against #39.
- Which to pick, Science: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Science at #16 against #96.
- Which to pick, Long context: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Long context at #34 against #95.
- Which to pick, Factuality: As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Factuality at #6 against #103.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 leads GPT-4.1 in Abstraction (ARC) at #10 against #85.

As of Oct 14, 2026, GPT-4.1 is a former state-of-the-art holder in Long context (since May 11, 2025; sources LMArena Text (style-controlled, longer query); methodology v1.0).

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).