# DeepSeek V3.2 Exp vs GPT-5.4

As of Oct 15, 2026, DeepSeek V3.2 Exp leads GPT-5.4 in 0 of 5 shared categories.

DeepSeek V3.2 Exp: $0.30500000000000005 per 1M blended tokens.

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

DeepSeek V3.2 Exp: open weights.

GPT-5.4: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V3.2 Exp in General LLM at #28 against #91.
- Which to pick, Reasoning: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V3.2 Exp in Reasoning at #29 against #81.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V3.2 Exp in Coding › Web dev at #55 against #98.
- Which to pick, Long context: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V3.2 Exp in Long context at #34 against #81.
- Which to pick, Factuality: As of Oct 15, 2026, GPT-5.4 leads DeepSeek V3.2 Exp in Factuality at #6 against #73.

As of Oct 15, 2026, DeepSeek V3.2 Exp is a former state-of-the-art holder in Reasoning (since Nov 17, 2025; sources LMArena Text (style-controlled, hard prompts); 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).