# Gemini 3.1 Pro Preview vs GPT-6 Luna

As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in 6 of 8 shared categories: General LLM, Reasoning, Science, Long context, Factuality, and Abstraction (ARC).

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

GPT-6 Luna: $0.19999999999999998 per 1M blended tokens.

Gemini 3.1 Pro Preview: closed weights.

GPT-6 Luna: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in General LLM at #15 against #65.
- Which to pick, Reasoning: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in Reasoning at #14 against #61.
- Which to pick, Science: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in Science at #7 against #33.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, GPT-6 Luna leads Gemini 3.1 Pro Preview in Coding › Web dev at #29 against #58.
- Which to pick, Long context: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in Long context at #12 against #61.
- Which to pick, Vision: As of Oct 14, 2026, GPT-6 Luna leads Gemini 3.1 Pro Preview in Vision at #17 against #25.
- Which to pick, Factuality: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in Factuality at #18 against #39.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, Gemini 3.1 Pro Preview leads GPT-6 Luna in Abstraction (ARC) at #2 against #22.

As of Oct 14, 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 14, 2026, GPT-6 Luna is state of the art on best per dollar in Coding (since Oct 14, 2026; sources Terminal-Bench 4.0; methodology v1.0).