# Claude Haiku 4.5 vs Gemini 3.1 Pro Preview

As of Oct 15, 2026, Claude Haiku 4.5 leads Gemini 3.1 Pro Preview in 0 of 7 shared categories.

Claude Haiku 4.5: $2.0000000000000004 per 1M blended tokens.

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

Claude Haiku 4.5: closed weights.

Gemini 3.1 Pro Preview: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in General LLM at #15 against #133.
- Which to pick, Reasoning: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Reasoning at #14 against #119.
- Which to pick, Science: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Science at #7 against #109.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Coding › Web dev at #63 against #103.
- Which to pick, Long context: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Long context at #12 against #107.
- Which to pick, Factuality: As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Factuality at #21 against #125.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Gemini 3.1 Pro Preview leads Claude Haiku 4.5 in Abstraction (ARC) at #2 against #78.

As of Oct 15, 2026, Claude Haiku 4.5 is ranked #78 in Abstraction (ARC) (since Oct 15, 2026; sources ARC-AGI; methodology v1.0).

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).