# Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview

As of Oct 14, 2026, Claude Sonnet 4.6 leads Gemini 3.1 Pro Preview in 2 of 8 shared categories: Coding › Web dev and Vision.

Claude Sonnet 4.6: $6 per 1M blended tokens.

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

Claude Sonnet 4.6: closed weights.

Gemini 3.1 Pro Preview: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in General LLM at #15 against #32.
- Which to pick, Reasoning: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in Reasoning at #14 against #20.
- Which to pick, Science: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in Science at #7 against #50.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, Claude Sonnet 4.6 leads Gemini 3.1 Pro Preview in Coding › Web dev at #41 against #58.
- Which to pick, Long context: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in Long context at #12 against #20.
- Which to pick, Vision: As of Oct 14, 2026, Claude Sonnet 4.6 leads Gemini 3.1 Pro Preview in Vision at #23 against #25.
- Which to pick, Factuality: As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in Factuality at #18 against #34.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, Gemini 3.1 Pro Preview leads Claude Sonnet 4.6 in Abstraction (ARC) at #2 against #23.

As of Oct 14, 2026, Claude Sonnet 4.6 is a former state-of-the-art holder in Long context (since Mar 19, 2026; sources LMArena Text (style-controlled, longer query); methodology v1.0).

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).