# Claude Haiku 4.5 vs GPT-4O Mini

As of Oct 14, 2026, Claude Haiku 4.5 leads GPT-4O Mini in 1 of 2 shared categories: Science.

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

GPT-4O Mini: $0.26249999999999996 per 1M blended tokens.

Claude Haiku 4.5: closed weights.

GPT-4O Mini: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, GPT-4O Mini leads Claude Haiku 4.5 in General LLM at #9 against #104.
- Which to pick, Science: As of Oct 14, 2026, Claude Haiku 4.5 leads GPT-4O Mini in Science at #109 against #161.

As of Oct 14, 2026, Claude Haiku 4.5 is ranked #78 in Abstraction (ARC) (since Oct 14, 2026; sources ARC-AGI; methodology v1.0).

As of Oct 14, 2026, GPT-4O Mini is ranked #9 in General LLM (since Oct 14, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).