# GPT-5.4 vs Qwen3 5 397B A17b

As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in 6 of 6 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, and Factuality.

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

Qwen3 5 397B A17b: $1.2750000000000001 per 1M blended tokens.

GPT-5.4: closed weights.

Qwen3 5 397B A17b: open weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in General LLM at #28 against #66.
- Which to pick, Reasoning: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in Reasoning at #29 against #64.
- Which to pick, Science: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in Science at #16 against #53.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in Coding › Web dev at #55 against #72.
- Which to pick, Long context: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in Long context at #34 against #60.
- Which to pick, Factuality: As of Oct 15, 2026, GPT-5.4 leads Qwen3 5 397B A17b in Factuality at #6 against #59.

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).

As of Oct 15, 2026, Qwen3 5 397B A17b is ranked #53 in Science (since Oct 15, 2026; sources GPQA Diamond; methodology v1.0).