# DeepSeek V4.1 Flash vs GPT-5.4

As of Oct 15, 2026, DeepSeek V4.1 Flash leads GPT-5.4 in 4 of 7 shared categories: Reasoning, Coding › Web dev, Long context, and Abstraction (ARC).

DeepSeek V4.1 Flash: $0.23463 per 1M blended tokens.

GPT-5.4: $5.625 per 1M blended tokens.

DeepSeek V4.1 Flash: open weights.

GPT-5.4: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V4.1 Flash in General LLM at #28 against #29.
- Which to pick, Reasoning: As of Oct 15, 2026, DeepSeek V4.1 Flash leads GPT-5.4 in Reasoning at #27 against #29.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V4.1 Flash in Science at #16 against #36.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, DeepSeek V4.1 Flash leads GPT-5.4 in Coding › Web dev at #19 against #55.
- Which to pick, Long context: As of Oct 15, 2026, DeepSeek V4.1 Flash leads GPT-5.4 in Long context at #32 against #34.
- Which to pick, Factuality: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V4.1 Flash in Factuality at #6 against #22.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, DeepSeek V4.1 Flash leads GPT-5.4 in Abstraction (ARC) at #8 against #10.

As of Oct 15, 2026, DeepSeek V4.1 Flash is state of the art on best per dollar in General LLM (since Oct 14, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).

As of Oct 15, 2026, GPT-5.4 is a former state-of-the-art holder in General LLM (since Apr 10, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0).