GPT-5.1vsQwen3.5

GPT-5.1
Qwen3.5
Specifications
Parameters
397B
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
25%
Coding
SWE-Bench Verified
76.3%
76.4%Best
Multilingual coding
SWE-Bench Multilingual
69.3%
Agentic terminal coding
Terminal-Bench 2.0
52.5%
Web browsing
BrowseComp
69%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
28.7%
Science
GPQA Diamond
88.1%
88.4%Best
Agentic computer use
OSWorld-Verified
62.2%
Chart reasoning
CharXiv Reasoning
80.8%
Multimodal reasoning
MMMU-Pro
79%
Multimodal
MMMU
76%
85%Best
Community preference (code)
Arena Elo (Code)
1391
Overview
CompanyOpenAIQwen
Release dateNov 12 2025Feb 16 2026
AccessProprietaryOpen Weight

Which is better: GPT-5.1 or Qwen3.5?

Qwen3.5 leads GPT-5.1 on 3 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMMU). GPT-5.1 shipped 96 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.

GPT-5.1 is proprietary, while Qwen3.5 is open weight.

On SWE-Bench Verified, Qwen3.5 leads at 76.4% vs GPT-5.1 at 76.3%. On GPQA Diamond, Qwen3.5 leads at 88.4% vs GPT-5.1 at 88.1%. On MMMU, Qwen3.5 leads at 85% vs GPT-5.1 at 76%.

Frequently asked questions

GPT-5.1 was released by OpenAI on Nov 12 2025.

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

Qwen3.5 leads on SWE-Bench Verified — GPT-5.1 76.3% vs Qwen3.5 76.4%.

Qwen3.5 leads on GPQA Diamond — GPT-5.1 88.1% vs Qwen3.5 88.4%.

GPT-5.1 is a proprietary model released by OpenAI. Qwen3.5 is an open weight model released by Qwen.

Other comparisons