GPT-5.4-ProvsQwen3.5

GPT-5.4-Pro
Qwen3.5
Specifications
Parameters
397B
Context window
1M
Benchmarks
Coding
SWE-Bench Verified
76.4%
Multilingual coding
SWE-Bench Multilingual
69.3%
Agentic terminal coding
Terminal-Bench 2.0
52.5%
Web browsing
BrowseComp
89.3%Best
69%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
28.7%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
58.7%
Abstract reasoning
ARC-AGI-2
83.3%
Advanced math
FrontierMath · Tier 1–3
50%
Advanced math
FrontierMath · Tier 4
38%
Science
GPQA Diamond
94.4%Best
88.4%
Agentic computer use
OSWorld-Verified
62.2%
Knowledge work
GDPval (win/tie rate)
82%
Chart reasoning
CharXiv Reasoning
80.8%
Multimodal reasoning
MMMU-Pro
79%
Multimodal
MMMU
85%
Overview
CompanyOpenAIQwen
Release dateMar 5 2026Feb 16 2026
AccessProprietaryOpen Weight

Which is better: GPT-5.4-Pro or Qwen3.5?

GPT-5.4-Pro leads Qwen3.5 on 2 of the 2 benchmarks they both report (BrowseComp, GPQA Diamond). Qwen3.5 shipped 17 days before GPT-5.4-Pro, so benchmark comparisons should account for the intervening progress.

GPT-5.4-Pro is proprietary, while Qwen3.5 is open weight.

On BrowseComp, GPT-5.4-Pro leads at 89.3% vs Qwen3.5 at 69%. On GPQA Diamond, GPT-5.4-Pro leads at 94.4% vs Qwen3.5 at 88.4%.

Frequently asked questions

GPT-5.4-Pro was released by OpenAI on Mar 5 2026.

Qwen3.5 was released by Qwen on Feb 16 2026.

GPT-5.4-Pro leads on GPQA Diamond — GPT-5.4-Pro 94.4% vs Qwen3.5 88.4%.

GPT-5.4-Pro is a proprietary model released by OpenAI. Qwen3.5 is an open weight model released by Qwen.

Other comparisons