# Gemini 3.1 Pro Preview vs GPT-4.1

As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Long context, Factuality, and Abstraction (ARC).

Gemini 3.1 Pro Preview: $4.5 per 1M blended tokens.

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

Gemini 3.1 Pro Preview: closed weights.

GPT-4.1: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in General LLM at #15 against #130.
- Which to pick, Reasoning: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Reasoning at #14 against #132.
- Which to pick, Math: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Math at #3 against #39.
- Which to pick, Science: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Science at #7 against #96.
- Which to pick, Long context: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Long context at #12 against #124.
- Which to pick, Factuality: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Factuality at #21 against #136.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Gemini 3.1 Pro Preview leads GPT-4.1 in Abstraction (ARC) at #2 against #85.

As of Oct 15, 2026, Gemini 3.1 Pro Preview is state of the art on best per dollar in Math (since Oct 14, 2026; sources Humanity's Last Exam; methodology v1.0).

As of Oct 15, 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).